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

    Neuronpedia

    INDEX
    Explanations

    file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (mut
    -0.07
    (identifier
    -0.06
    '$
    -0.06
    astle
    -0.06
    825
    -0.06
    аж
    -0.06
    725
    -0.06
    uss
    -0.06
    rent
    -0.06
     Dim
    -0.06
    POSITIVE LOGITS
    __.
    0.27
    __/
    0.08
    	Image
    0.06
    Exact
    0.06
    ||(
    0.06
     Harmon
    0.06
     gripping
    0.06
    InteractionEnabled
    0.06
     System
    0.06
    _deinit
    0.06
    Act Density 0.000%

    No Known Activations