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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     confuse
    -0.07
    neo
    -0.07
    ӯ
    -0.07
    ٻ
    -0.06
    ZN
    -0.06
    igious
    -0.06
    ("."
    -0.06
    esimal
    -0.06
    ibal
    -0.06
     mundane
    -0.06
    POSITIVE LOGITS
    甲状腺
    0.07
     sched
    0.07
    佩戴
    0.07
     insol
    0.07
    (att
    0.07
     stud
    0.07
     anguish
    0.07
    )):↵
    0.07
    を使用
    0.07
     יע
    0.07
    Act Density 0.000%

    No Known Activations