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

    Neuronpedia

    INDEX
    Explanations

    database indexing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Employee
    -0.07
     togg
    -0.06
     shepherd
    -0.06
    thinking
    -0.06
     Followers
    -0.06
    Design
    -0.06
     작품
    -0.06
     typo
    -0.06
     Diagnostic
    -0.06
    .Password
    -0.06
    POSITIVE LOGITS
     IOCTL
    0.07
    /gen
    0.07
    istence
    0.06
    .layoutControlItem
    0.06
    (agent
    0.06
    .pat
    0.06
     Autom
    0.06
    -fin
    0.06
    ísk
    0.06
    .Ge
    0.06
    Act Density 0.029%

    No Known Activations