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

    Neuronpedia

    INDEX
    Explanations

    to + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Error
    0.34
     hexadecimal
    0.32
    '
    0.32
    _
    0.32
     overfitting
    0.31
    Error
    0.30
    indexOf
    0.30
    pecific
    0.30
     bearish
    0.30
    q
    0.30
    POSITIVE LOGITS
     mennesker
    0.31
     persones
    0.30
    сторі
    0.30
     trabalho
    0.30
     או
    0.30
     мото
    0.30
     ロ
    0.29
    рі
    0.29
     ਅਤੇ
    0.29
     trabajo
    0.29
    Act Density 0.094%

    No Known Activations