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

    Neuronpedia

    INDEX
    Explanations

    numeric and string conversions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    設備の
    0.41
    行人
    0.39
    akot
    0.38
     Anlagen
    0.38
     майже
    0.38
    Hp
    0.38
    Oui
    0.38
    拁
    0.37
    மிகு
    0.36
     接
    0.36
    POSITIVE LOGITS
     womb
    0.43
    PEZ
    0.41
    prototype
    0.40
     طويل
    0.36
     novas
    0.35
     novela
    0.35
     Detail
    0.34
     interesses
    0.34
     chats
    0.33
    వాన్ని
    0.33
    Act Density 0.005%

    No Known Activations