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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Targets
    -0.07
    030
    -0.07
    (messages
    -0.07
     foam
    -0.07
    ків
    -0.06
     Foam
    -0.06
    .decorators
    -0.06
    _ATTRIBUTES
    -0.06
     precio
    -0.06
    pron
    -0.06
    POSITIVE LOGITS
     قادر
    0.07
    ใหม
    0.07
    ư
    0.06
    ................
    0.06
     naken
    0.06
     Rory
    0.06
     Jazeera
    0.06
     embarrassing
    0.06
     userName
    0.06
     gunshot
    0.06
    Act Density 0.026%

    No Known Activations