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

    Neuronpedia

    INDEX
    Explanations

    wise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рел
    -0.07
    تون
    -0.07
     passenger
    -0.06
    손
    -0.06
    lahoma
    -0.06
     fik
    -0.06
    ことに
    -0.06
    _helpers
    -0.06
    -types
    -0.06
     fullName
    -0.06
    POSITIVE LOGITS
    ALT
    0.07
    	ERR
    0.07
     Increases
    0.06
    Transmission
    0.06
    	raw
    0.06
    tas
    0.06
    FRAME
    0.06
    ALS
    0.06
    _prom
    0.06
     Τ
    0.06
    Act Density 0.010%

    No Known Activations