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

    Neuronpedia

    INDEX
    Explanations

    Survey/year

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    γου
    -0.06
    riority
    -0.06
    attrs
    -0.06
    	lbl
    -0.05
    apore
    -0.05
    خرج
    -0.05
     ¬
    -0.05
     css
    -0.05
    verbatim
    -0.05
    zv
    -0.05
    POSITIVE LOGITS
    acerb
    0.08
    載
    0.07
    -week
    0.07
    ArrayType
    0.07
     aerospace
    0.06
    :'
    0.06
    (ra
    0.06
     ary
    0.06
    先生
    0.06
    _aff
    0.06
    Act Density 0.049%

    No Known Activations