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

    Neuronpedia

    INDEX
    Explanations

    fall into repetitive patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    payers
    0.77
    edly
    0.76
    substring
    0.76
    riente
    0.74
    शाला
    0.72
    டத்தில்
    0.72
    ertos
    0.71
    ئے
    0.71
    thoughts
    0.70
    izador
    0.70
    POSITIVE LOGITS
     asleep
    1.76
     prey
    1.38
     victim
    1.31
     fall
    1.25
    Fall
    1.21
    FALL
    1.12
     Fall
    1.11
     falls
    1.10
     apart
    1.07
    afel
    1.05
    Act Density 0.032%

    No Known Activations