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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    褓
    -0.07
     complains
    -0.07
    _conf
    -0.07
     Tomb
    -0.07
    🚧
    -0.07
    .CreateIndex
    -0.06
     atual
    -0.06
    -class
    -0.06
     enfer
    -0.06
    _completion
    -0.06
    POSITIVE LOGITS
    ,on
    0.08
    打折
    0.07
    福利
    0.07
    flix
    0.07
     Significant
    0.07
    uffles
    0.07
    ଘ
    0.07
    ificantly
    0.07
    (sh
    0.07
     �
    0.07
    Act Density 0.005%

    No Known Activations