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

    Neuronpedia

    INDEX
    Explanations

    conflict

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     newspaper
    -0.07
     comfortably
    -0.06
     Globe
    -0.06
     judgments
    -0.06
    .Tween
    -0.06
     Vanity
    -0.06
    .NewRequest
    -0.06
    ")->
    -0.06
    (NULL
    -0.06
     offend
    -0.06
    POSITIVE LOGITS
     toplam
    0.07
     tutar
    0.07
    committee
    0.07
     транспор
    0.06
     сопров
    0.06
    riangle
    0.06
     Heg
    0.06
     比
    0.06
    .Enabled
    0.06
    <L
    0.06
    Act Density 0.126%

    No Known Activations