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

    Neuronpedia

    INDEX
    Explanations

    verb + positive descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     건설
    0.52
    ER
    0.50
    Í
    0.49
    utto
    0.48
     추
    0.45
    d
    0.45
    da
    0.45
    v
    0.45
    U
    0.44
    ra
    0.43
    POSITIVE LOGITS
     autorisation
    0.48
    娼
    0.47
    ᱒
    0.46
     personagens
    0.45
     mengakses
    0.45
     personnage
    0.45
     responden
    0.45
     Direito
    0.44
     commencent
    0.43
     oui
    0.43
    Act Density 0.001%

    No Known Activations