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

    Neuronpedia

    INDEX
    Explanations

    grappling hook

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wanton
    0.41
     shear
    0.39
    gment
    0.38
    真是
    0.37
     টিকে
    0.37
    ลอด
    0.36
     survives
    0.36
     imperfect
    0.36
     advances
    0.36
     lizard
    0.36
    POSITIVE LOGITS
    eteen
    0.41
    ಿರಿ
    0.41
    Ձ
    0.41
     PRL
    0.40
    槑
    0.40
     кру
    0.40
     TOTAL
    0.40
     bulat
    0.39
    總
    0.39
     jum
    0.39
    Act Density 0.000%

    No Known Activations