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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Widget
    -0.07
    .productId
    -0.07
     welcomes
    -0.07
    才能
    -0.07
    ')->
    -0.06
    Monkey
    -0.06
     Hooks
    -0.06
     Monkey
    -0.06
    _challenge
    -0.06
     AGE
    -0.06
    POSITIVE LOGITS
    inosaur
    0.07
     loft
    0.06
     essentially
    0.06
    endra
    0.06
    million
    0.06
     vocal
    0.06
     identical
    0.06
    })}↵
    0.06
    뿐
    0.06
    wayne
    0.06
    Act Density 0.036%

    No Known Activations