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

    Neuronpedia

    INDEX
    Explanations

    cracks, fissures, damage, tears

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    వన్
    0.45
     Tumblr
    0.43
     اداکار
    0.43
    权力
    0.42
    揽
    0.41
     Vanilla
    0.40
     afili
    0.40
     academic
    0.39
     düny
    0.39
     Academic
    0.39
    POSITIVE LOGITS
     cracks
    1.63
     cracking
    1.35
     cracked
    1.30
     fissures
    1.30
     fractures
    1.29
     crack
    1.28
    裂
    1.27
     fracture
    1.23
     damage
    1.13
    crack
    1.13
    Act Density 0.050%

    No Known Activations