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

    Neuronpedia

    INDEX
    Explanations

    Visual media descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    figur
    -0.06
     тва
    -0.06
    _fk
    -0.06
    .Priority
    -0.06
    _SHIFT
    -0.06
     turnout
    -0.06
     Mull
    -0.06
    LEE
    -0.06
     유형
    -0.06
    we
    -0.06
    POSITIVE LOGITS
    /details
    0.07
    ीं।
    0.07
    签
    0.07
     Installing
    0.07
    ونه
    0.07
     invoke
    0.07
     os
    0.06
    andoned
    0.06
    oline
    0.06
    Graphics
    0.06
    Act Density 0.005%

    No Known Activations