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

    Neuronpedia

    INDEX
    Explanations

    wife

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    okes
    -0.08
     charter
    -0.07
    ACTER
    -0.07
    anker
    -0.07
    Formula
    -0.07
     interruption
    -0.06
    CHAN
    -0.06
    aque
    -0.06
     рух
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Alison
    0.07
    -user
    0.07
     нес
    0.06
    (epoch
    0.06
     pasado
    0.06
    .fixed
    0.06
    -tone
    0.06
    .HttpStatus
    0.06
    (station
    0.06
    better
    0.06
    Act Density 0.337%

    No Known Activations