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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grenade
    -0.08
    竞
    -0.07
     port
    -0.07
     اللبن
    -0.07
     tone
    -0.07
     anatom
    -0.06
    �
    -0.06
    type
    -0.06
    UInteger
    -0.06
     mutant
    -0.06
    POSITIVE LOGITS
    오
    0.07
    \Validation
    0.07
     verification
    0.07
    ائز
    0.07
     entire
    0.07
    енного
    0.07
    ext
    0.07
    Advertisement
    0.06
    ayas
    0.06
     GetCurrent
    0.06
    Act Density 0.001%

    No Known Activations