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

    Neuronpedia

    INDEX
    Explanations

    formatting and punctuation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     M
    1.14
     F
    0.98
     CA
    0.96
     MG
    0.93
     KR
    0.93
     AM
    0.92
     FR
    0.92
     SP
    0.91
     MN
    0.91
     CF
    0.91
    POSITIVE LOGITS
    ,”
    0.85
    ”,
    0.85
    ,“
    0.81
    ,’
    0.78
    -”
    0.76
     consum
    0.76
    ’,
    0.75
     stomachs
    0.74
    ),"
    0.74
    !”,
    0.73
    Act Density 0.000%

    No Known Activations