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

    Neuronpedia

    INDEX
    Explanations

    Code snippets involving disabling features

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Falsy
    -0.07
    Resolution
    -0.06
    _blocks
    -0.06
    _supply
    -0.06
    _goods
    -0.06
     남
    -0.06
    �
    -0.06
    erox
    -0.06
    relevant
    -0.06
     cooled
    -0.06
    POSITIVE LOGITS
     shell
    0.07
     شرقی
    0.06
     Zone
    0.06
     Here
    0.06
     pymysql
    0.06
    >")
    0.06
    varchar
    0.06
    .IsDBNull
    0.06
     echt
    0.06
    RegularExpression
    0.06
    Act Density 0.080%

    No Known Activations