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

    Neuronpedia

    INDEX
    Explanations

    scientific units and measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     imposes
    -0.07
    756
    -0.07
    okie
    -0.07
    Built
    -0.06
     panels
    -0.06
    واج
    -0.06
     Mul
    -0.06
    strap
    -0.06
    很多
    -0.06
    ати
    -0.06
    POSITIVE LOGITS
    (disposing
    0.07
    변
    0.06
     valueForKey
    0.06
     komen
    0.06
    access
    0.06
     familia
    0.06
     nonatomic
    0.06
    dens
    0.06
     війни
    0.06
    (namespace
    0.06
    Act Density 0.007%

    No Known Activations