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

    Neuronpedia

    INDEX
    Explanations

    distance from landmark or qualifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dosages
    0.42
    fromj
    0.41
    existent
    0.39
     hypertensive
    0.39
    elben
    0.38
    লালের
    0.38
    ভূত
    0.38
    混凝
    0.38
    tpVar
    0.37
    जरीवाल
    0.37
    POSITIVE LOGITS
    সির
    0.44
     an
    0.40
    O
    0.39
    В
    0.39
     Privat
    0.38
     on
    0.38
     at
    0.37
     popul
    0.36
     via
    0.36
    সি
    0.36
    Act Density 0.000%

    No Known Activations