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

    Neuronpedia

    INDEX
    Explanations

    arts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (gca
    -0.07
    ทาน
    -0.06
     arrests
    -0.06
    ьми
    -0.06
     повед
    -0.06
    768
    -0.06
    TexCoord
    -0.06
    778
    -0.06
    .........
    -0.06
    ческое
    -0.06
    POSITIVE LOGITS
    _dom
    0.07
     PAS
    0.07
     уг
    0.07
    elligence
    0.06
    Outlined
    0.06
     Jess
    0.06
     Specialist
    0.06
    .so
    0.06
     твор
    0.06
     NFS
    0.06
    Act Density 0.009%

    No Known Activations