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

    Neuronpedia

    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    figure
    -0.06
     徒歩
    -0.06
    184
    -0.06
     kalk
    -0.06
    Hostname
    -0.06
     Peace
    -0.06
     advertise
    -0.06
     свою
    -0.06
     manages
    -0.06
    .temp
    -0.06
    POSITIVE LOGITS
     thanh
    0.07
    stants
    0.07
    _zip
    0.07
    .В
    0.06
    ेशन
    0.06
    Instances
    0.06
     immedi
    0.06
    вая
    0.06
    _unc
    0.06
     Salad
    0.06
    Act Density 0.000%

    No Known Activations