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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CONSTANT
    -0.07
     Spurs
    -0.07
     دور
    -0.07
     dato
    -0.06
    uning
    -0.06
     shading
    -0.06
    =line
    -0.06
    .ge
    -0.06
    -times
    -0.06
     매
    -0.06
    POSITIVE LOGITS
    Monad
    0.07
    理解
    0.06
    Studies
    0.06
     rozvoj
    0.06
    implicit
    0.06
     Terrorism
    0.06
    ografia
    0.06
    нями
    0.06
    าข
    0.06
    bakan
    0.06
    Act Density 0.000%

    No Known Activations