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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Eddie
    -0.07
    Attend
    -0.07
     Athena
    -0.07
    쒸
    -0.07
     Xen
    -0.06
    -risk
    -0.06
     المسي
    -0.06
     제가
    -0.06
     Devils
    -0.06
     있게
    -0.06
    POSITIVE LOGITS
    olvers
    0.08
    tracts
    0.07
    款
    0.07
    etas
    0.07
    ReceiveMemoryWarning
    0.07
    ograph
    0.07
    wrapper
    0.07
     prohibition
    0.07
    기술
    0.07
    .ModelSerializer
    0.06
    Act Density 0.055%

    No Known Activations