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

    Neuronpedia

    INDEX
    Explanations

    red

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .LinearLayoutManager
    -0.07
     나가
    -0.07
     sentido
    -0.06
    vinces
    -0.06
     نش
    -0.06
    ول
    -0.06
    -held
    -0.06
    EMA
    -0.06
    طف
    -0.06
     نیر
    -0.06
    POSITIVE LOGITS
     wrongful
    0.07
     psychological
    0.07
    .WebControls
    0.07
    .Val
    0.06
     humiliation
    0.06
     associates
    0.06
    _Val
    0.06
    Ver
    0.06
     Honor
    0.06
     equipment
    0.06
    Act Density 0.006%

    No Known Activations