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

    Neuronpedia

    INDEX
    Explanations

    slice of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ngrx
    0.99
    Dsp
    0.98
    instr
    0.98
     flea
    0.97
     NMR
    0.94
     sculpture
    0.93
    0.92
     captcha
    0.90
    엡
    0.90
     ።
    0.90
    POSITIVE LOGITS
    ahan
    0.92
    oven
    0.90
    Ą
    0.89
    Kh
    0.89
    yah
    0.89
     oficiais
    0.88
    Luc
    0.87
    ą
    0.87
    Quint
    0.87
     hitt
    0.87
    Act Density 0.001%

    No Known Activations