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

    Neuronpedia

    INDEX
    Explanations

    Math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     täglich
    -0.09
     النص
    -0.09
     Ecommerce
    -0.08
     Emails
    -0.08
    _EMAIL
    -0.08
     weekdays
    -0.08
     smoothies
    -0.08
     이메일
    -0.08
     البريد
    -0.08
     escalation
    -0.08
    POSITIVE LOGITS
    -axis
    0.13
    _axis
    0.11
    -radius
    0.11
    _radius
    0.11
     determined
    0.11
     radius
    0.10
     axes
    0.10
     axis
    0.10
    Axis
    0.10
    确定
    0.10
    Act Density 0.051%

    No Known Activations