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

    Neuronpedia

    INDEX
    Explanations

    statistical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    0.69
    f
    0.55
    u
    0.54
    in
    0.52
    te
    0.49
    nial
    0.49
    gol
    0.47
    ation
    0.47
    o
    0.46
    e
    0.46
    POSITIVE LOGITS
     harnessed
    0.55
     bacterias
    0.54
     personnes
    0.52
     microorganism
    0.48
     bacter
    0.48
    種の
    0.47
     edilir
    0.47
     ziek
    0.47
     procesu
    0.46
     ligament
    0.46
    Act Density 0.004%

    No Known Activations