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

    Neuronpedia

    INDEX
    Explanations

    Go package flags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lickr
    0.23
    4
    0.22
    2
    0.21
     incluido
    0.21
    ત
    0.21
    迅速
    0.21
    വും
    0.20
    ágico
    0.20
    の
    0.20
    9
    0.20
    POSITIVE LOGITS
     testAvg
    0.22
    Ꮡ
    0.20
    ുവരി
    0.20
     memeriksa
    0.20
     mathbf
    0.20
    <unused1100>
    0.19
     prudence
    0.19
     inspe
    0.19
     從
    0.19
    曉
    0.19
    Act Density 0.001%

    No Known Activations