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

    Neuronpedia

    INDEX
    Explanations

    code syntax and errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    וב
    0.44
    lake
    0.41
    वाह
    0.40
     besonders
    0.39
     Polymers
    0.37
     profondes
    0.36
     caram
    0.36
     dyes
    0.36
    aped
    0.35
    butanol
    0.35
    POSITIVE LOGITS
    ндекс
    0.39
    Ե
    0.39
    ੫
    0.39
     next
    0.38
     демон
    0.38
     다음
    0.38
     majestic
    0.38
     nextline
    0.38
     inaccuracy
    0.37
    缐
    0.37
    Act Density 0.000%

    No Known Activations