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

    Neuronpedia

    INDEX
    Explanations

    shared resources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -reviewed
    -0.28
    大ä¸ĵ
    -0.26
    jian
    -0.25
     allerg
    -0.24
    elib
    -0.24
    [unit
    -0.24
     Rom
    -0.24
    dana
    -0.24
     Thomson
    -0.23
    appers
    -0.23
    POSITIVE LOGITS
    upe
    0.30
    uard
    0.28
    chemas
    0.28
    æįĨç»ij
    0.27
     uÄŁra
    0.27
    nice
    0.27
    ime
    0.27
    _nan
    0.27
    Defense
    0.26
    æĥ³åĬŀæ³ķ
    0.26
    Act Density 0.003%

    No Known Activations