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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gettext
    -0.07
     distracted
    -0.07
     futbol
    -0.07
     metod
    -0.07
     balk
    -0.07
    妮
    -0.06
     control
    -0.06
    物理
    -0.06
     jí
    -0.06
     retarded
    -0.06
    POSITIVE LOGITS
    _hide
    0.07
    endencies
    0.06
     createSelector
    0.06
     söyledi
    0.06
    tiler
    0.06
     Uns
    0.06
    assign
    0.06
     MASK
    0.06
    ोड
    0.05
    Permissions
    0.05
    Act Density 0.008%

    No Known Activations