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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    免费
    -0.07
    那样
    -0.06
     �
    -0.06
     ValueError
    -0.06
    toPromise
    -0.06
     été
    -0.06
    ampie
    -0.06
     �
    -0.06
    Active
    -0.06
     novo
    -0.06
    POSITIVE LOGITS
     reasoning
    0.07
     trades
    0.06
    $s
    0.06
     villain
    0.06
    ickest
    0.06
    _references
    0.06
     Prem
    0.06
    ,cv
    0.06
     checking
    0.06
    formData
    0.06
    Act Density 0.004%

    No Known Activations