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
     Aux
    -0.07
     Тим
    -0.06
     cyc
    -0.06
     currentValue
    -0.06
    夫
    -0.06
     Rad
    -0.06
     �
    -0.06
     rozp
    -0.06
    apt
    -0.06
     kali
    -0.06
    POSITIVE LOGITS
    threads
    0.07
    Participant
    0.07
     Artists
    0.06
    .registry
    0.06
    estation
    0.06
     hombres
    0.06
    _OPEN
    0.06
     petites
    0.06
    知道
    0.06
     Argentine
    0.06
    Act Density 0.021%

    No Known Activations