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

    Neuronpedia

    INDEX
    Explanations

    graphics code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GAP
    -0.07
     Gat
    -0.07
    _Char
    -0.06
     tact
    -0.06
     intimidation
    -0.06
     sword
    -0.06
     layouts
    -0.06
     turret
    -0.06
    ibration
    -0.06
    _malloc
    -0.06
    POSITIVE LOGITS
     resent
    0.07
     conserv
    0.06
    شاء
    0.06
     promin
    0.06
     interruptions
    0.06
    _cent
    0.06
    代理
    0.06
     çevir
    0.06
    ouv
    0.06
     bipartisan
    0.06
    Act Density 0.010%

    No Known Activations