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

    Neuronpedia

    INDEX
    Explanations

    signature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +$
    -0.08
    bish
    -0.07
    ｢
    -0.07
    parity
    -0.06
     واس
    -0.06
     markdown
    -0.06
    系統
    -0.06
    vanced
    -0.06
    -users
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
     ingen
    0.06
    аза
    0.06
     dram
    0.06
     شعر
    0.06
    rende
    0.06
    Pri
    0.06
     agon
    0.06
     hij
    0.06
    搜
    0.06
    .setColumn
    0.06
    Act Density 0.000%

    No Known Activations