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

    Neuronpedia

    INDEX
    Explanations

    ready and facing consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    0.48
    ﻓ
    0.39
    рт
    0.35
    ﻟ
    0.34
    га
    0.34
    ۰
    0.34
    곽
    0.33
    ній
    0.33
     malzem
    0.33
    го
    0.32
    POSITIVE LOGITS
    m
    0.45
    to
    0.37
    面临
    0.36
     decommissioning
    0.36
    ర
    0.34
     infamous
    0.33
    はい
    0.33
     indefinite
    0.33
     be
    0.33
    ುಂಬ
    0.33
    Act Density 0.644%

    No Known Activations