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

    Neuronpedia

    INDEX
    Explanations

    personal realizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    liers
    -0.07
     nhu
    -0.07
    Coach
    -0.07
    orna
    -0.06
    г
    -0.06
    alach
    -0.06
    افع
    -0.06
     ATK
    -0.06
     ".$_
    -0.06
    xing
    -0.06
    POSITIVE LOGITS
     lesbienne
    0.07
     fichier
    0.06
    ftar
    0.06
     flawed
    0.06
     (�
    0.06
     kích
    0.06
    

↵
    0.06
    Vect
    0.06
    Incomplete
    0.06
    draulic
    0.06
    Act Density 0.058%

    No Known Activations