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

    Neuronpedia

    INDEX
    Explanations

    item id and configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alamy
    0.40
     nc
    0.40
     ശു
    0.39
     xếp
    0.37
     Fung
    0.37
     vaginal
    0.37
     wię
    0.35
     Formal
    0.35
    agc
    0.35
    วี
    0.35
    POSITIVE LOGITS
    SMS
    0.43
    ClientID
    0.42
    Pip
    0.42
     Conditioning
    0.41
     conditioning
    0.40
     SMS
    0.39
    см
    0.39
    pipelines
    0.39
     Clients
    0.38
     Deployment
    0.38
    Act Density 0.003%

    No Known Activations