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

    Neuronpedia

    INDEX
    Explanations

    disclaimers of endorsement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     politische
    0.55
     działalności
    0.55
     書い
    0.53
     интерес
    0.52
     fondant
    0.52
     cytoplas
    0.51
     instituciones
    0.51
     פע
    0.51
     букмекердик
    0.51
     αριθ
    0.50
    POSITIVE LOGITS
    6
    0.62
    W
    0.59
    8
    0.57
    en
    0.56
    /
    0.56
    7
    0.56
    X
    0.56
    5
    0.56
    ↵
    0.55
    4
    0.55
    Act Density 0.001%

    No Known Activations