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

    Neuronpedia

    INDEX
    Explanations

    find

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elif
    -0.06
    Derived
    -0.06
     Enh
    -0.06
    них
    -0.06
     demeanor
    -0.06
    enarios
    -0.06
     Impro
    -0.06
    	byte
    -0.06
     servicio
    -0.06
     whichever
    -0.06
    POSITIVE LOGITS
     find
    0.07
    landır
    0.07
    _found
    0.07
     proposition
    0.06
    gunta
    0.06
     mun
    0.06
     poured
    0.06
    exceptions
    0.06
     intermitt
    0.06
    apters
    0.06
    Act Density 0.021%

    No Known Activations