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

    Neuronpedia

    INDEX
    Explanations

    problem statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    permitted
    0.39
    rom
    0.39
    uge
    0.39
    nu
    0.38
    imps
    0.37
     Za
    0.36
    iju
    0.36
    nington
    0.36
    ureen
    0.36
    art
    0.36
    POSITIVE LOGITS
     solved
    0.74
     problèmes
    0.73
     PROBLEMS
    0.72
     problemas
    0.72
     solvers
    0.71
    ग्रस्त
    0.71
     problems
    0.70
     solver
    0.70
     unsolved
    0.67
     해결
    0.66
    Act Density 0.029%

    No Known Activations