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

    Neuronpedia

    INDEX
    Explanations

    ~

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tab
    -0.07
     매매가
    -0.07
     Tb
    -0.07
    kr
    -0.07
     Burk
    -0.06
     envy
    -0.06
     Fishing
    -0.06
    Checkbox
    -0.06
    佛
    -0.06
     pud
    -0.06
    POSITIVE LOGITS
    .DIS
    0.08
    .IN
    0.07
    .COLOR
    0.07
    etection
    0.07
     IMPLIED
    0.06
    175
    0.06
    -mode
    0.06
     عم
    0.06
    ющихся
    0.06
    .updated
    0.06
    Act Density 0.000%

    No Known Activations