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

    Neuronpedia

    INDEX
    Explanations

    programming parameters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ')))
    -0.08
    .Orientation
    -0.07
     �
    -0.07
    .Println
    -0.07
    Pear
    -0.07
    .member
    -0.07
    #+#+
    -0.07
    _RUNTIME
    -0.06
    .bounds
    -0.06
    μιλος
    -0.06
    POSITIVE LOGITS
     get
    0.07
     za
    0.06
    stu
    0.06
    -wise
    0.06
    ;display
    0.06
    fred
    0.06
     tür
    0.05
     trustees
    0.05
     offsets
    0.05
    ITT
    0.05
    Act Density 0.037%

    No Known Activations