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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getInfo
    -0.07
     prox
    -0.07
     distingu
    -0.06
     sonraki
    -0.06
     inté
    -0.06
     เส
    -0.06
    /object
    -0.06
     ندار
    -0.06
    ulton
    -0.06
    riba
    -0.06
    POSITIVE LOGITS
     Dealer
    0.07
    jectories
    0.07
     Face
    0.07
    /tab
    0.06
    REA
    0.06
     Breaking
    0.06
     Looking
    0.06
     worth
    0.06
     DL
    0.06
     accelerator
    0.06
    Act Density 0.001%

    No Known Activations