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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “ease of use,” i.e. phrases highlighting usability.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     theres
    -0.07
    něn
    -0.07
     तरफ
    -0.06
    ่าเป
    -0.06
    خواست
    -0.06
    erable
    -0.06
     autogenerated
    -0.06
     lavish
    -0.06
    `s
    -0.06
     ник
    -0.06
    POSITIVE LOGITS
     art
    0.07
    Bond
    0.07
    Priority
    0.07
    업
    0.07
    Wind
    0.07
     cost
    0.07
    Eat
    0.07
     организации
    0.07
     Ruth
    0.06
    stone
    0.06
    Act Density 0.005%

    No Known Activations