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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Than
    -0.07
     yourself
    -0.06
    鲀
    -0.06
    ᠴ
    -0.06
    떔
    -0.06
    솎
    -0.06
    emm
    -0.06
    <!
    -0.06
     Kelley
    -0.06
    -mult
    -0.06
    POSITIVE LOGITS
     examines
    0.07
    制约
    0.07
     MediaType
    0.07
    Raise
    0.06
    .checkBox
    0.06
    랙
    0.06
    稳步推进
    0.06
     Nora
    0.06
    AndServe
    0.06
    irut
    0.06
    Act Density 0.042%

    No Known Activations