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

    Neuronpedia

    INDEX
    Explanations

    Reese, rees, reese's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ೆಂದು
    0.37
    ains
    0.37
     کوي
    0.37
     일으
    0.36
     primary
    0.36
     vela
    0.35
    掻
    0.35
     stochastic
    0.34
    quirements
    0.33
     canto
    0.33
    POSITIVE LOGITS
     Reese
    0.60
     Witherspoon
    0.57
     Reece
    0.49
     Pieces
    0.47
     Ре
    0.40
    rees
    0.40
    Pieces
    0.40
    鄢
    0.40
     Peanut
    0.39
    dataType
    0.39
    Act Density 0.003%

    No Known Activations