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

    Neuronpedia

    INDEX
    Explanations

    ice crystals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    disable
    0.45
    ٽ
    0.43
    つける
    0.40
    ない
    0.40
     destroy
    0.39
    තුරු
    0.39
    DISABLE
    0.39
    場合は
    0.38
     場合
    0.38
     الدولية
    0.38
    POSITIVE LOGITS
    opathies
    0.46
     ciencias
    0.45
    lems
    0.45
    חים
    0.43
    чери
    0.42
    eft
    0.42
    曾
    0.42
    ozy
    0.42
     sabes
    0.42
    дер
    0.41
    Act Density 0.000%

    No Known Activations