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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .comments
    -0.08
    ся
    -0.07
    (_)
    -0.07
    sic
    -0.07
    絕
    -0.07
    수
    -0.07
    Fed
    -0.07
    མ
    -0.07
     Jonathan
    -0.07
    ();)
    -0.07
    POSITIVE LOGITS
    >R
    0.08
     מאחורי
    0.07
    掮
    0.07
     bothering
    0.07
    akening
    0.07
    岘
    0.07
     bored
    0.07
    老板
    0.07
    organized
    0.07
     kleinen
    0.07
    Act Density 0.003%

    No Known Activations