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

    Neuronpedia

    INDEX
    Explanations

    HTML closing tags

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

    HTML or code tags

    np_acts-logits-general · gemini-2.0-flash

    html tags or decrees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Expose
    -0.55
    τικός
    -0.52
    ⓘ
    -0.52
    cipit
    -0.51
     GenerationType
    -0.51
    OrNil
    -0.51
    Javadoc
    -0.49
    /**
    -0.47
     Instinct
    -0.45
    ModelAttribute
    -0.44
    POSITIVE LOGITS
     }}$}
    0.64
    "</
    0.63
    ."</
    0.63
     }}"></
    0.63
     المعيارى
    0.62
    tvguidetime
    0.60
    math
    0.60
    eschön
    0.57
    zegor
    0.57
    สือ
    0.57
    Act Density 0.113%

    No Known Activations