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
    putation
    -0.07
    faces
    -0.07
     rhet
    -0.06
    ierung
    -0.06
     Measurement
    -0.06
     map
    -0.06
    bootstrap
    -0.06
    ovie
    -0.06
    /language
    -0.06
    pute
    -0.06
    POSITIVE LOGITS
    ...
    0.06
     い
    0.06
    _softc
    0.06
    #'
    0.06
    ---↵
    0.06
    aseña
    0.06
    ="">↵
    0.06
    ス
    0.06
     Venezuelan
    0.06
     αποτε
    0.06
    Act Density 0.053%

    No Known Activations