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

    Neuronpedia

    INDEX
    Explanations

    generalizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    临
    -0.07
    �
    -0.07
    .member
    -0.07
    /Y
    -0.06
    طبيق
    -0.06
    -stat
    -0.06
     RSA
    -0.06
    RSA
    -0.06
    婆
    -0.06
    臨
    -0.06
    POSITIVE LOGITS
     nikdy
    0.06
     seç
    0.06
     Equation
    0.06
    .setProgress
    0.06
     filenames
    0.06
     zeigt
    0.05
     quil
    0.05
    -analysis
    0.05
     rating
    0.05
     ");↵↵
    0.05
    Act Density 0.161%

    No Known Activations