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

    Neuronpedia

    INDEX
    Explanations

    subroutines or variable declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VALUE
    0.47
    FOCUS
    0.47
     bạn
    0.46
     قيمة
    0.46
     liquidate
    0.44
     بہ
    0.44
    Posted
    0.44
     ramo
    0.43
     país
    0.43
    @",
    0.43
    POSITIVE LOGITS
    ünft
    0.48
     Tener
    0.47
    inger
    0.47
    ungere
    0.46
     হাসপাত
    0.46
    terbury
    0.45
     అలీ
    0.45
    arin
    0.44
    ară
    0.44
    aes
    0.44
    Act Density 0.000%

    No Known Activations