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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     뒤
    -0.07
     bundan
    -0.07
     dừng
    -0.07
     contrato
    -0.06
    ä
    -0.06
    堡
    -0.06
    يلا
    -0.06
    lara
    -0.06
    ーダ
    -0.06
     pán
    -0.06
    POSITIVE LOGITS
    .ENTER
    0.07
     unemployed
    0.07
    .Marshal
    0.06
    _CONDITION
    0.06
    MFLOAT
    0.06
    \Command
    0.06
     SAF
    0.06
     beloved
    0.06
    \App
    0.06
     Pharm
    0.06
    Act Density 0.046%

    No Known Activations