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

    Neuronpedia

    INDEX
    Explanations

    Generate creative text formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anymore
    0.49
     опа
    0.45
     American
    0.42
    mation
    0.40
     отказа
    0.39
     sensations
    0.39
     intentions
    0.39
     pamphlets
    0.38
     executives
    0.38
     African
    0.38
    POSITIVE LOGITS
    Czas
    0.46
    قیه
    0.46
    ചി
    0.45
     cela
    0.45
     Punkte
    0.45
     membut
    0.44
    Zug
    0.44
    Kelas
    0.44
    㑔
    0.44
    UNKNOWN
    0.44
    Act Density 0.000%

    No Known Activations