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

    Neuronpedia

    INDEX
    Explanations

    set

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    经典
    -0.08
     klasik
    -0.08
    14
    -0.08
    šč
    -0.07
     arches
    -0.07
     diferen
    -0.07
    FINITE
    -0.07
     classics
    -0.07
     differences
    -0.07
     clássico
    -0.07
    POSITIVE LOGITS
     setter
    0.15
    .setter
    0.13
     변경
    0.12
     Setter
    0.12
     менять
    0.12
    変更
    0.11
    Setter
    0.11
    /change
    0.11
     overwrite
    0.11
     업데이트
    0.11
    Act Density 0.005%

    No Known Activations