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

    Neuronpedia

    INDEX
    Explanations

    why questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    illus
    -0.06
    headline
    -0.06
     runaway
    -0.06
    back
    -0.06
    osomes
    -0.06
    itas
    -0.06
     torso
    -0.06
    -backed
    -0.06
     Oliveira
    -0.06
     cosas
    -0.06
    POSITIVE LOGITS
    .RowIndex
    0.07
    .AddModelError
    0.07
     acoustic
    0.06
    _VERTICAL
    0.06
    ANTITY
    0.06
    %)
    0.06
    *',
    0.06
     точ
    0.06
     PTR
    0.06
    UInteger
    0.06
    Act Density 0.108%

    No Known Activations