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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ORIENTATION
    -0.08
     bleak
    -0.07
     Aw
    -0.06
     EEG
    -0.06
    /Q
    -0.06
     Beet
    -0.06
     robbed
    -0.06
    -0.06
    ovement
    -0.06
    $arity
    -0.06
    POSITIVE LOGITS
     Actions
    0.07
    -pol
    0.07
    hões
    0.06
     стар
    0.06
    دو
    0.06
     много
    0.06
     old
    0.06
     Companies
    0.06
    Solo
    0.06
     организации
    0.06
    Act Density 0.000%

    No Known Activations