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

    Neuronpedia

    INDEX
    Explanations

    feast for, feast on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    1.15
    9
    1.05
    i
    1.01
    3
    0.96
    ü
    0.90
    ре
    0.88
    hdf
    0.88
    re
    0.87
    .
    0.87
    There
    0.85
    POSITIVE LOGITS
     feasts
    1.36
     feast
    1.34
    та
    1.31
     Feast
    1.15
    س
    1.12
    ната
    1.10
    '
    1.07
    ના
    1.06
    ית
    1.02
    ‘
    1.02
    Act Density 0.000%

    No Known Activations