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

    Neuronpedia

    INDEX
    Explanations

    personal opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .
    -0.56
    lan
    -0.53
    ↵↵
    -0.52
    ti
    -0.51
    d
    -0.50
    ou
    -0.49
    ?
    -0.49
    ,
    -0.49
    and
    -0.47
    mo
    -0.47
    POSITIVE LOGITS
     Infórmanos
    0.90
    ✨:
    0.86
    SBATCH
    0.85
     Taktlose
    0.85
    ^(@)
    0.84
     Efq
    0.84
     AssemblyCulture
    0.82
     kaynağından
    0.82
    IndentedString
    0.81
    RenderAtEndOf
    0.79
    Act Density 0.379%

    No Known Activations