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

    Neuronpedia

    INDEX
    Explanations

    recommend

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -development
    -0.07
     Πρό
    -0.07
    улю
    -0.06
     podí
    -0.06
    CLS
    -0.06
     plagiarism
    -0.06
     compil
    -0.06
     фар
    -0.06
     Микола
    -0.06
     площ
    -0.06
    POSITIVE LOGITS
    Cook
    0.07
     Cook
    0.07
    (get
    0.07
     Randall
    0.06
    .propTypes
    0.06
    Luc
    0.06
    ần
    0.06
    RESH
    0.06
    WithPath
    0.06
     transformers
    0.06
    Act Density 0.009%

    No Known Activations