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

    Neuronpedia

    INDEX
    Explanations

    C++ code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    salt
    0.39
    [:,
    0.37
    $>
    0.37
    $<
    0.37
    çamento
    0.34
    鹹
    0.34
    বীন্দ্র
    0.34
    斂
    0.34
    ómo
    0.34
    盐
    0.34
    POSITIVE LOGITS
     dail
    0.41
     quotid
    0.39
    墾
    0.39
    󠁮
    0.39
     ಕಂಡ
    0.39
    Ｑ
    0.38
     Q
    0.38
    ustellen
    0.38
     стаў
    0.38
    顧
    0.37
    Act Density 0.000%

    No Known Activations