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

    Neuronpedia

    INDEX
    Explanations

    code/numerical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    grave
    -0.32
     crt
    -0.29
    åŀĴ
    -0.26
     appointments
    -0.26
    æ»ĭ
    -0.25
    sexual
    -0.25
    agus
    -0.25
    alysis
    -0.24
    aha
    -0.24
    éĿĴéĵľ
    -0.24
    POSITIVE LOGITS
    æĪĺ
    0.28
    lesc
    0.26
    è´´è¿ij
    0.26
    å½Ī
    0.26
    تاÙĨ
    0.26
    =sub
    0.25
    BACK
    0.25
    JM
    0.25
    Cond
    0.25
    åħī线
    0.25
    Act Density 0.022%

    No Known Activations