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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LINE
    -0.07
    lij
    -0.07
    痣
    -0.07
     vẻ
    -0.06
     physique
    -0.06
    _BS
    -0.06
     בצורה
    -0.06
    zza
    -0.06
    ?>↵
    -0.06
    擔心
    -0.06
    POSITIVE LOGITS
     strongly
    0.07
    ㈹
    0.07
     languages
    0.07
     anticip
    0.07
     Nacional
    0.07
    CppGuid
    0.07
     líder
    0.07
     CASCADE
    0.07
    껐
    0.06
    𬶋
    0.06
    Act Density 0.009%

    No Known Activations