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

    Neuronpedia

    INDEX
    Explanations

    actions and system operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    1.17
    lo
    1.16
    ted
    1.16
    о
    1.13
    ли
    1.12
    ε
    1.11
    их
    1.05
    to
    1.05
    ই
    1.05
    torn
    1.05
    POSITIVE LOGITS
    heets
    1.74
    heet
    1.39
    creens
    1.39
    ysteem
    1.25
    ources
    1.20
     esophagus
    1.19
    essions
    1.17
    hift
    1.15
    criptors
    1.14
     adhesives
    1.12
    Act Density 0.321%

    No Known Activations