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

    Neuronpedia

    INDEX
    Explanations

    questions starting with what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Is
    0.43
    Are
    0.42
     Is
    0.40
    Equ
    0.40
    Ig
    0.39
    Precis
    0.39
    Ident
    0.39
     দেবযানীর
    0.39
    »
    0.38
     Equally
    0.38
    POSITIVE LOGITS
     razy
    0.48
     sane
    0.47
     හොඳ
    0.44
     beter
    0.44
     meagre
    0.43
     melhor
    0.43
    irin
    0.43
     pouvait
    0.43
     besser
    0.42
     modos
    0.42
    Act Density 0.006%

    No Known Activations