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

    Neuronpedia

    INDEX
    Explanations

    systemharmfulunstable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     distortion
    0.39
    延
    0.39
    AnyCPU
    0.38
     darin
    0.38
     Bele
    0.38
     aberration
    0.38
     solvation
    0.38
    袒
    0.37
     دوم
    0.37
     Tons
    0.37
    POSITIVE LOGITS
    КО
    0.38
    uene
    0.37
    السلام
    0.37
    expect
    0.37
     esperaba
    0.37
     Казино
    0.36
     consecuencia
    0.36
     expect
    0.36
    CLICK
    0.36
    关键
    0.35
    Act Density 0.000%

    No Known Activations