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

    Neuronpedia

    INDEX
    Explanations

    channeling inner self

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    双眼
    -0.08
    معرف
    -0.07
    砣
    -0.07
    حرص
    -0.07
    +%
    -0.07
    @if
    -0.07
    🎻
    -0.07
    CUR
    -0.06
    _conn
    -0.06
     cookbook
    -0.06
    POSITIVE LOGITS
    �
    0.08
     Effects
    0.07
    anned
    0.07
    apyrus
    0.07
    tero
    0.06
     acres
    0.06
    𝙘
    0.06
    랒
    0.06
    leared
    0.06
    arry
    0.06
    Act Density 0.077%

    No Known Activations