Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    details or elements that illustrate comparisons or distinctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by comparative "that" or period

    np_acts-logits-general · gemini-2.0-flash

    distinguishing between two

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /**
    -0.80
    Xna
    -0.72
    zzleHttp
    -0.70
    tdessen
    -0.69
    ритори
    -0.64
    -0.64
    UnknownFieldSet
    -0.63
     незавершена
    -0.62
    ocino
    -0.62
     שוליים
    -0.59
    POSITIVE LOGITS
    后者
    1.14
     letz
    0.84
     latter
    0.81
     Erster
    0.64
     تضيفلها
    0.61
     respectivamente
    0.58
     concernant
    0.56
     suivantes
    0.55
     keduanya
    0.55
     respectivement
    0.55
    Act Density 0.606%

    No Known Activations