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

    Neuronpedia

    INDEX
    Explanations

    citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _feat
    -0.07
     sistemi
    -0.06
    alars
    -0.06
    implementation
    -0.06
    樣
    -0.06
    nod
    -0.06
     собі
    -0.06
     �
    -0.06
    lan
    -0.06
    nect
    -0.06
    POSITIVE LOGITS
    Intialized
    0.07
     و
    0.07
    _ARCHIVE
    0.07
     signin
    0.07
    .bs
    0.06
    .act
    0.06
    Compound
    0.06
    .serialize
    0.06
     Bach
    0.06
     ImageView
    0.06
    Act Density 0.050%

    No Known Activations