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

    Neuronpedia

    INDEX
    Explanations

    how to read

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pracę
    0.57
    ANY
    0.51
    אם
    0.47
    ต่ำ
    0.46
    Institutional
    0.45
    🛶
    0.45
    ન્યા
    0.45
    casualties
    0.44
    ו
    0.44
    Ⲟ
    0.44
    POSITIVE LOGITS
     captivated
    0.52
    isive
    0.50
     bizarre
    0.48
     lauf
    0.47
    地上
    0.46
     Typh
    0.45
     transpired
    0.45
    is
    0.43
     nombre
    0.43
     decrypted
    0.43
    Act Density 0.000%

    No Known Activations