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

    Neuronpedia

    INDEX
    Explanations

    confrontarsi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    args
    0.54
    culoskeletal
    0.47
     conveying
    0.46
    rots
    0.45
    皮膚
    0.45
    بل
    0.44
    who
    0.44
     যিনি
    0.44
     barking
    0.44
     who
    0.43
    POSITIVE LOGITS
     STREET
    0.53
    SAFETY
    0.52
     Seagate
    0.49
     Heid
    0.48
     SAFETY
    0.48
     luar
    0.47
     সংস্কার
    0.47
     COMMIT
    0.47
     Jalan
    0.47
     Siegel
    0.47
    Act Density 0.000%

    No Known Activations