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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chemistry
    -0.07
    bras
    -0.06
    ihn
    -0.06
    -CS
    -0.06
    izens
    -0.06
     flute
    -0.06
     payoff
    -0.06
     circum
    -0.06
    ику
    -0.06
    embedding
    -0.06
    POSITIVE LOGITS
    ISHED
    0.07
     uso
    0.07
     石
    0.07
     kä
    0.07
    ениями
    0.06
    سه
    0.06
     approaching
    0.06
     kicked
    0.06
    theValue
    0.06
    ніш
    0.06
    Act Density 0.003%

    No Known Activations