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

    Neuronpedia

    INDEX
    Explanations

    important considerations removed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    trat
    0.47
     goats
    0.46
    tau
    0.44
    tavern
    0.43
    heny
    0.43
    ynamics
    0.43
    omeres
    0.43
    oxet
    0.42
    depression
    0.42
    amsu
    0.42
    POSITIVE LOGITS
    Average
    0.48
    본
    0.47
    ب
    0.45
    Qatar
    0.44
     vasta
    0.43
     आण
    0.42
    十足
    0.42
    Из
    0.41
    All
    0.40
     jeder
    0.40
    Act Density 0.000%

    No Known Activations