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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _anchor
    -0.07
     Pascal
    -0.06
     desea
    -0.06
    frei
    -0.06
     diagrams
    -0.06
    .debian
    -0.06
    \base
    -0.06
     determinant
    -0.06
    _paper
    -0.06
    .setImage
    -0.06
    POSITIVE LOGITS
    ϛ
    0.07
    (pub
    0.07
     recall
    0.07
     HACK
    0.06
     exports
    0.06
    洛阳
    0.06
    (environment
    0.06
    认
    0.06
    )","
    0.06
    婴
    0.06
    Act Density 0.087%

    No Known Activations