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

    Neuronpedia

    INDEX
    Explanations

    this * or this into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ].
    0.88
    '
    0.86
     certains
    0.78
    ],
    0.77
    :
    0.77
    ;
    0.75
    ्ड
    0.74
    ech
    0.73
    Mach
    0.73
    moc
    0.71
    POSITIVE LOGITS
     with
    1.10
     as
    1.10
    with
    1.09
    IVACON
    1.06
     μέσω
    1.05
     från
    1.01
     путем
    1.01
     WITH
    0.98
     ज़र
    0.98
     melalui
    0.96
    Act Density 0.212%

    No Known Activations