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

    Neuronpedia

    INDEX
    Explanations

    scholarships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _basename
    -0.06
     directory
    -0.06
     미
    -0.06
    packet
    -0.06
     Cookbook
    -0.06
     Romeo
    -0.06
    ynos
    -0.06
    _estimator
    -0.06
    以上
    -0.05
    ما
    -0.05
    POSITIVE LOGITS
     Intr
    0.07
     extrav
    0.07
     barr
    0.07
    伤
    0.07
     objection
    0.07
     ori
    0.07
     prec
    0.06
     pract
    0.06
     :-
    0.06
     sare
    0.06
    Act Density 0.069%

    No Known Activations