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

    Neuronpedia

    INDEX
    Explanations

    polytopes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     taught
    -0.07
     acı
    -0.06
     Features
    -0.06
     targets
    -0.06
     Marl
    -0.06
    ricia
    -0.06
    .assertj
    -0.06
    _demo
    -0.06
    ける
    -0.06
    άντα
    -0.06
    POSITIVE LOGITS
    -points
    0.07
    _ENTRIES
    0.06
    .inspect
    0.06
     Ju
    0.06
    уп
    0.06
     �
    0.06
     PP
    0.06
     CAST
    0.06
    .ib
    0.06
     endors
    0.06
    Act Density 0.005%

    No Known Activations