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

    Neuronpedia

    INDEX
    Explanations

    issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \uD
    -0.07
    ocê
    -0.07
    redd
    -0.07
    DEV
    -0.07
    xcb
    -0.06
    _IDENTIFIER
    -0.06
     Thủ
    -0.06
     \<
    -0.06
    حب
    -0.06
     minced
    -0.06
    POSITIVE LOGITS
    936
    0.07
     Policies
    0.07
    番
    0.07
    xr
    0.07
     penalties
    0.07
     Panasonic
    0.07
    @@
    0.07
    lastName
    0.07
    анти
    0.07
     شود
    0.07
    Act Density 0.000%

    No Known Activations