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

    Neuronpedia

    INDEX
    Explanations

    Movement verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zdrav
    -0.07
    Marvel
    -0.06
     strife
    -0.06
    Australia
    -0.06
     bathtub
    -0.06
     prominently
    -0.06
    prediction
    -0.06
     underwear
    -0.06
    langs
    -0.06
    ournemouth
    -0.06
    POSITIVE LOGITS
    _KEY
    0.07
    /code
    0.07
     arresting
    0.07
     Acid
    0.07
     ide
    0.07
    UPLOAD
    0.07
    oning
    0.06
     criminal
    0.06
    -users
    0.06
     imposing
    0.06
    Act Density 0.043%

    No Known Activations