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

    Neuronpedia

    INDEX
    Explanations

    crypto package paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beforeDir
    0.45
     movimentos
    0.42
     equalize
    0.42
     गिव
    0.40
     uniformed
    0.40
     movimientos
    0.40
    phenoxymethyl
    0.40
    নেল
    0.39
    اصمة
    0.39
    Helping
    0.39
    POSITIVE LOGITS
    +=
    0.45
     Stellar
    0.44
    ress
    0.42
    awab
    0.39
    寂
    0.39
     เชื่อ
    0.38
    vie
    0.37
     της
    0.36
     confused
    0.36
     való
    0.36
    Act Density 0.000%

    No Known Activations