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

    Neuronpedia

    INDEX
    Explanations

    perme

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    箭
    -0.08
     thorough
    -0.07
    .arc
    -0.07
     LONG
    -0.07
    ulance
    -0.07
    のでしょう
    -0.07
    >C
    -0.07
    .ac
    -0.07
     demonstr
    -0.07
    粤港澳
    -0.06
    POSITIVE LOGITS
    _meta
    0.07
     Session
    0.07
    ٪
    0.07
    فرد
    0.07
    yx
    0.07
    Managed
    0.07
    �
    0.07
    けて
    0.07
     reiterated
    0.07
    عظ
    0.07
    Act Density 0.009%

    No Known Activations