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

    Neuronpedia

    INDEX
    Explanations

    oh/th sounds

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     textbooks
    -0.06
    ıb
    -0.06
    stand
    -0.06
     tapping
    -0.06
     }}/
    -0.06
     delivers
    -0.06
     dance
    -0.06
     guard
    -0.06
    自由
    -0.06
     speaks
    -0.06
    POSITIVE LOGITS
    [x
    0.08
    （笑
    0.08
    ンフ
    0.07
    onavir
    0.07
    (reg
    0.07
     �
    0.07
     UserManager
    0.06
    滿
    0.06
    _MUTEX
    0.06
    __$
    0.06
    Act Density 0.010%

    No Known Activations