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

    Neuronpedia

    INDEX
    Explanations

    text input elements (textarea)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ver
    0.48
     in
    0.47
    ums
    0.46
    that
    0.45
     avanzada
    0.44
     diamant
    0.44
    ként
    0.43
    linger
    0.43
    ave
    0.43
    brand
    0.43
    POSITIVE LOGITS
     datetime
    0.51
    스
    0.50
    ંતુ
    0.49
     verificare
    0.48
    nnc
    0.48
    Haryana
    0.48
     diffusione
    0.48
    ფორმა
    0.47
     pressur
    0.46
    REFLECTION
    0.46
    Act Density 0.001%

    No Known Activations