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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     substance
    -0.08
    至
    -0.08
    ideon
    -0.07
     additive
    -0.07
     booklet
    -0.07
    igit
    -0.07
    損
    -0.07
     estos
    -0.07
    १�
    -0.06
    かの
    -0.06
    POSITIVE LOGITS
     few
    0.07
     validationResult
    0.07
    ////////////////////////////////////////////////////////////////////////
    0.06
    (tcp
    0.06
     phái
    0.06
    Inject
    0.06
     rich
    0.06
    "];
    0.06
    (Control
    0.06
     rw
    0.06
    Act Density 0.053%

    No Known Activations