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

    Neuronpedia

    INDEX
    Explanations

    metal manipulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    liquer
    0.74
    ขาด
    0.71
     descre
    0.69
     syst
    0.69
     arbeid
    0.66
     dus
    0.66
     Vacuum
    0.66
     legitt
    0.66
    Vacuum
    0.65
     despl
    0.65
    POSITIVE LOGITS
     up
    0.78
     immune
    0.78
     خمس
    0.73
    ປັນ
    0.73
     feeders
    0.72
    ToPlot
    0.71
     AsyncTask
    0.71
    imm
    0.69
    هد
    0.69
    up
    0.69
    Act Density 0.001%

    No Known Activations