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

    Neuronpedia

    INDEX
    Explanations

    brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Todo
    -0.07
     Т
    -0.07
     validators
    -0.07
    Composer
    -0.07
     대한
    -0.06
    خواست
    -0.06
     Additionally
    -0.06
    ,y
    -0.06
     cautious
    -0.06
     Responsive
    -0.06
    POSITIVE LOGITS
    __↵
    0.07
     cliffs
    0.06
     mensen
    0.06
     slam
    0.06
    らの
    0.06
    练
    0.06
     Allies
    0.06
     ділян
    0.06
    EMENT
    0.06
     lump
    0.06
    Act Density 0.027%

    No Known Activations