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

    Neuronpedia

    INDEX
    Explanations

    server definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ***
    0.48
     нача
    0.44
    ***
    0.44
     Crystall
    0.41
    ****
    0.40
     truncate
    0.40
     dol
    0.39
     satisfacer
    0.39
    esper
    0.38
     lezen
    0.38
    POSITIVE LOGITS
    omitempty
    0.40
     flimsy
    0.39
    েইলি
    0.38
     docile
    0.38
    ater
    0.37
     कार्यरत
    0.36
    ന്യൂ
    0.36
    Marshaler
    0.36
     entangled
    0.35
    responding
    0.35
    Act Density 0.000%

    No Known Activations