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

    Neuronpedia

    INDEX
    Explanations

    interprets actions or feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ą
    0.40
    oną
    0.37
    oczes
    0.37
     Lambert
    0.35
    intercept
    0.34
    iculas
    0.34
    åg
    0.33
     अल्ट्रा
    0.33
    ettore
    0.33
     ultraf
    0.33
    POSITIVE LOGITS
    Nep
    0.42
     intuitively
    0.41
    Conn
    0.40
     చేశ
    0.40
     needy
    0.39
    TouchableOpacity
    0.38
     {[
    0.38
     unintentionally
    0.38
     unnecessarily
    0.38
    二维
    0.38
    Act Density 0.001%

    No Known Activations