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

    Neuronpedia

    INDEX
    Explanations

    action descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oldCount
    0.44
    outlet
    0.41
     lemak
    0.41
    жан
    0.41
     Jung
    0.39
    жем
    0.38
     amts
    0.37
     jung
    0.37
    oldCount
    0.37
     Mid
    0.36
    POSITIVE LOGITS
     GE
    0.42
    TEL
    0.40
    ABLE
    0.39
    Alaska
    0.39
    GE
    0.38
    isson
    0.38
     Action
    0.38
    యు
    0.38
    WERS
    0.38
    ULS
    0.38
    Act Density 0.025%

    No Known Activations