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

    Neuronpedia

    INDEX
    Explanations

    product advertisements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    edes
    -0.08
    िह
    -0.07
    Boost
    -0.07
    セット
    -0.06
    愿
    -0.06
    розум
    -0.06
    不可
    -0.06
     lstm
    -0.06
    olith
    -0.06
    ovolta
    -0.06
    POSITIVE LOGITS
     CX
    0.07
    ucks
    0.06
     Career
    0.06
     digit
    0.06
    ULSE
    0.06
     علیه
    0.06
     réuss
    0.06
     Floyd
    0.06
    .Claims
    0.06
    orer
    0.05
    Act Density 0.049%

    No Known Activations