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

    Neuronpedia

    INDEX
    Explanations

    negative opinions or things related to poor quality experiences

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lier
    -0.47
    mata
    -0.45
     */
    -0.41
    ga
    -0.41
    /**/
    -0.41
    ens
    -0.41
    ly
    -0.40
    ับ
    -0.40
    のですか
    -0.40
    ess
    -0.40
    POSITIVE LOGITS
    ientôt
    0.74
     ComVisible
    0.71
    \"></
    0.69
     Италијани
    0.68
     unknownFields
    0.65
    DebuggerNonUser
    0.64
     capes
    0.63
    ::_('
    0.63
    actionMode
    0.63
     africaine
    0.62
    Act Density 0.903%

    No Known Activations