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

    Neuronpedia

    INDEX
    Explanations

    privacy and time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ადგენ
    0.46
    RELATIVA
    0.46
    ريبي
    0.45
     moeil
    0.44
     instancia
    0.43
    скохозяй
    0.42
     TRANSPORTURI
    0.42
    Ꮡ
    0.42
    říve
    0.42
     esposo
    0.42
    POSITIVE LOGITS
     for
    0.67
     glazing
    0.51
    for
    0.50
     set
    0.50
     call
    0.50
     but
    0.49
    ید
    0.49
     naming
    0.49
     plaid
    0.49
     supernatural
    0.48
    Act Density 0.000%

    No Known Activations