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

    Neuronpedia

    INDEX
    Explanations

    how to do or how much

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     नस
    0.41
    跺
    0.38
    typicode
    0.38
     konular
    0.38
     finalement
    0.38
    ния
    0.38
     conseille
    0.37
    汋
    0.37
    ленный
    0.37
     presenceData
    0.37
    POSITIVE LOGITS
     much
    0.61
    much
    0.60
     did
    0.51
     many
    0.50
    Much
    0.50
     Much
    0.47
     does
    0.47
     do
    0.46
     dangerous
    0.46
     long
    0.46
    Act Density 0.017%

    No Known Activations