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

    Neuronpedia

    INDEX
    Explanations

    category

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ns
    -0.06
    _attrs
    -0.06
    Billy
    -0.06
    -law
    -0.06
    thic
    -0.06
    _message
    -0.06
     Washington
    -0.06
     sin
    -0.06
     Gul
    -0.06
    Toolbar
    -0.06
    POSITIVE LOGITS
     realloc
    0.08
     emlrt
    0.07
     århus
    0.07
     merch
    0.07
    isable
    0.06
     vergi
    0.06
     deserialize
    0.06
     قطر
    0.06
    enna
    0.06
    	vec
    0.06
    Act Density 0.041%

    No Known Activations