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

    Neuronpedia

    INDEX
    Explanations

    _align

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Update
    -0.08
     conscious
    -0.07
     mennes
    -0.07
    -century
    -0.07
    周期
    -0.07
    _items
    -0.06
     Valley
    -0.06
    λά
    -0.06
     visas
    -0.06
    ULD
    -0.06
    POSITIVE LOGITS
     شكل
    0.06
    位于
    0.06
     attest
    0.06
     ง
    0.06
    See
    0.06
    ogn
    0.06
    _ALIGN
    0.06
    ž
    0.06
    aln
    0.06
     wellbeing
    0.06
    Act Density 0.002%

    No Known Activations