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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     moll
    -0.07
    	Long
    -0.07
    	parse
    -0.07
    ᡝ
    -0.07
     wicked
    -0.07
    (inv
    -0.07
     wp
    -0.07
     zob
    -0.06
    [obj
    -0.06
    😷
    -0.06
    POSITIVE LOGITS
    	if
    0.07
     Eğer
    0.07
    횽
    0.07
    rieben
    0.07
     envisioned
    0.07
    덞
    0.07
    建�
    0.06
    흗
    0.06
    أوضاع
    0.06
    듄
    0.06
    Act Density 0.019%

    No Known Activations