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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _error
    -0.07
    ¥
    -0.07
    aç
    -0.07
    	alert
    -0.06
    uls
    -0.06
    criptors
    -0.06
    sterol
    -0.06
    +w
    -0.06
    osos
    -0.06
    DOCKER
    -0.06
    POSITIVE LOGITS
    ύπ
    0.06
    .Positive
    0.06
    ollect
    0.06
     audition
    0.06
    祭
    0.06
     inauguration
    0.06
    kind
    0.06
     ipt
    0.06
    Beautiful
    0.06
    ]initWith
    0.06
    Act Density 0.065%

    No Known Activations