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
     Annie
    -0.07
    란
    -0.06
    ANE
    -0.06
     cropped
    -0.06
    'O
    -0.06
    _WRAPPER
    -0.06
    γμα
    -0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -0.06
    _FOLDER
    -0.06
     Swim
    -0.06
    POSITIVE LOGITS
     può
    0.06
    Directories
    0.06
    _cats
    0.06
     uncertain
    0.06
    _xt
    0.06
     pp
    0.06
     interceptions
    0.06
    getElement
    0.06
    "?↵↵
    0.06
    CONTROL
    0.05
    Act Density 0.000%

    No Known Activations