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

    Neuronpedia

    INDEX
    Explanations

    like me, like GPT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     paździer
    0.55
    标识
    0.49
    蝈
    0.48
    官员
    0.47
    拍卖
    0.47
     partage
    0.46
    轶
    0.45
    利润
    0.45
     paysage
    0.45
     paisaje
    0.45
    POSITIVE LOGITS
    ih
    0.52
    insulin
    0.52
    my
    0.51
    both
    0.51
     emuls
    0.51
    iovascular
    0.49
    including
    0.49
     enzymatic
    0.48
     both
    0.48
    salt
    0.47
    Act Density 0.004%

    No Known Activations