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

    Neuronpedia

    INDEX
    Explanations

    partial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kot
    -0.07
     trophy
    -0.07
    َم
    -0.07
    _num
    -0.06
     Tup
    -0.06
     NES
    -0.06
    �
    -0.06
     summar
    -0.06
    Spawn
    -0.06
     Dare
    -0.06
    POSITIVE LOGITS
    _AST
    0.07
    >G
    0.07
    इसक
    0.07
     charts
    0.07
    RELATED
    0.07
     trimming
    0.07
    mesinin
    0.07
     partial
    0.07
     '\'
    0.06
    İL
    0.06
    Act Density 0.001%

    No Known Activations