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

    Neuronpedia

    INDEX
    Explanations

    system versioning and risk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cod
    0.46
    Cod
    0.45
     [
    0.42
    Solving
    0.42
     Service
    0.42
     Estud
    0.40
     Cho
    0.40
     Solving
    0.40
    Service
    0.39
     Release
    0.39
    POSITIVE LOGITS
    immersive
    0.44
     worsened
    0.43
     mustered
    0.41
     angered
    0.41
     অনুপ্র
    0.40
    ävät
    0.40
     biocompat
    0.39
     worsens
    0.39
     heightened
    0.39
    inspiring
    0.39
    Act Density 0.000%

    No Known Activations