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

    Neuronpedia

    INDEX
    Explanations

    pick

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    鹅
    -0.08
     לב
    -0.07
    /↵↵↵↵
    -0.07
    凭什么
    -0.07
    褥
    -0.06
     reinforcement
    -0.06
    消費
    -0.06
    )>=
    -0.06
     ihtiyaç
    -0.06
    ꪋ
    -0.06
    POSITIVE LOGITS
    Ant
    0.08
    bra
    0.07
    _note
    0.07
     Yoga
    0.07
     filmmakers
    0.07
     STR
    0.07
    legacy
    0.07
    $row
    0.07
     filmmaker
    0.06
    <dim
    0.06
    Act Density 0.008%

    No Known Activations