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

    Neuronpedia

    INDEX
    Explanations

    secret

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    approx
    -0.07
    ̆
    -0.07
    \Middleware
    -0.07
    ครบ
    -0.07
    &quot
    -0.06
     yardım
    -0.06
    _Mouse
    -0.06
     MSS
    -0.06
    xs
    -0.06
    授
    -0.06
    POSITIVE LOGITS
    γέν
    0.07
    	uint
    0.07
     injustice
    0.06
     قیمت
    0.06
     Roberts
    0.06
     метою
    0.06
     Diagnosis
    0.06
    (bind
    0.06
    上
    0.06
    emoth
    0.06
    Act Density 0.010%

    No Known Activations