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

    Neuronpedia

    INDEX
    Explanations

    ://

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _toggle
    -0.07
     Formal
    -0.06
    elligence
    -0.06
     Pointer
    -0.06
    _query
    -0.06
     Poetry
    -0.06
    PLUGIN
    -0.06
    _TO
    -0.06
     View
    -0.06
    mime
    -0.06
    POSITIVE LOGITS
     versa
    0.06
     sung
    0.06
     Neu
    0.06
     helt
    0.06
    ických
    0.06
    _Rem
    0.06
    (wp
    0.06
     discard
    0.06
     boa
    0.06
     tailor
    0.06
    Act Density 0.014%

    No Known Activations