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

    Neuronpedia

    INDEX
    Explanations

    U.S. legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    detach
    -0.07
     molded
    -0.06
    	damage
    -0.06
    sanitize
    -0.06
    俊
    -0.06
     Rolled
    -0.06
    IMITIVE
    -0.06
     Equals
    -0.06
    _FP
    -0.06
    Display
    -0.06
    POSITIVE LOGITS
     debates
    0.07
    svp
    0.06
     betr
    0.06
     六
    0.06
     gek
    0.06
    adě
    0.06
     doll
    0.06
    itra
    0.06
     questi
    0.06
     spons
    0.06
    Act Density 0.008%

    No Known Activations