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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Flux
    -0.07
    (lines
    -0.07
    ilk
    -0.07
    897
    -0.07
     Knoxville
    -0.07
     raids
    -0.06
    ею
    -0.06
    _scripts
    -0.06
     DEVICE
    -0.06
     alters
    -0.06
    POSITIVE LOGITS
    .bunifuFlatButton
    0.07
     Sponge
    0.07
     باشد
    0.07
    纸
    0.06
     Eval
    0.06
     Şubat
    0.06
     subtraction
    0.06
     compareTo
    0.06
    checkout
    0.06
     regrets
    0.06
    Act Density 0.025%

    No Known Activations