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

    Neuronpedia

    INDEX
    Explanations

    specific nouns or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Choose
    0.44
    containsKey
    0.42
     रोज़
    0.41
    ChooseServer
    0.40
    Charge
    0.39
    Give
    0.38
     சரிய
    0.38
    Cuenta
    0.38
    ContainsKey
    0.38
    Residence
    0.38
    POSITIVE LOGITS
     Watson
    0.47
     angst
    0.44
     aby
    0.42
     our
    0.41
     சதவீ
    0.41
     the
    0.41
     mars
    0.41
     again
    0.40
     factor
    0.39
     instead
    0.39
    Act Density 0.000%

    No Known Activations