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

    Neuronpedia

    INDEX
    Explanations

    allows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _tri
    -0.07
    ディ
    -0.07
     sacrific
    -0.07
     příro
    -0.07
    _si
    -0.07
    Fin
    -0.07
    iosper
    -0.06
     Tire
    -0.06
     bí
    -0.06
    阅
    -0.06
    POSITIVE LOGITS
     allows
    0.11
     allow
    0.10
    allow
    0.10
     Allow
    0.09
     allowing
    0.09
     allowed
    0.09
    Allows
    0.09
     Allows
    0.08
    Allow
    0.08
    Aw
    0.08
    Act Density 0.049%

    No Known Activations