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

    Neuronpedia

    INDEX
    Explanations

    ent, entra, entrer, in, around

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    1.44
    ла
    1.43
    ться
    1.32
    נ
    1.30
    ك
    1.22
    ى
    1.19
    ين
    1.18
    し
    1.18
    ه
    1.15
    은
    1.12
    POSITIVE LOGITS
    demand
    1.30
    diabetes
    1.29
    staking
    1.27
    stained
    1.27
    deposit
    1.20
    depression
    1.19
    dice
    1.17
    drivers
    1.16
    del
    1.16
    don
    1.16
    Act Density 0.000%

    No Known Activations