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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     letz
    -0.07
    maxlength
    -0.07
    (classes
    -0.07
    一种
    -0.06
    陶
    -0.06
     ح
    -0.06
    linkplain
    -0.06
     Bars
    -0.06
    nehmer
    -0.06
     Bale
    -0.06
    POSITIVE LOGITS
     YY
    0.07
    _gem
    0.07
     merge
    0.06
     abilities
    0.06
     Firm
    0.06
    _DISPATCH
    0.06
     PLUS
    0.06
    .Location
    0.06
     candidacy
    0.06
    uality
    0.06
    Act Density 0.218%

    No Known Activations