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

    Neuronpedia

    INDEX
    Explanations

    will also

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    を獲得
    0.44
     unexplained
    0.42
     acquires
    0.41
     spacecraft
    0.39
     Determines
    0.39
     possesses
    0.39
     quelconque
    0.39
     inexplicable
    0.38
     unchallenged
    0.38
     countless
    0.37
    POSITIVE LOGITS
     give
    0.75
     also
    0.70
     też
    0.66
     також
    0.64
    also
    0.63
     også
    0.61
     myös
    0.61
     גם
    0.60
     आल्सो
    0.60
     также
    0.59
    Act Density 0.002%

    No Known Activations