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

    Neuronpedia

    INDEX
    Explanations

    Machine learning algorithms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     жүзеге
    -0.09
    ellisen
    -0.08
    berries
    -0.08
     marvel
    -0.08
     nopeasti
    -0.08
     દ્વ
    -0.08
    artikel
    -0.08
    жен
    -0.08
     rapidement
    -0.08
     гар
    -0.07
    POSITIVE LOGITS
     :=
    0.08
    ieden
    0.07
    XA
    0.07
    رم
    0.07
     phr
    0.07
     exigir
    0.07
    yb
    0.07
     tendencies
    0.07
     interpre
    0.07
    FSM
    0.07
    Act Density 0.000%

    No Known Activations