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

    Neuronpedia

    INDEX
    Explanations

    programming code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aliment
    0.49
    cou
    0.46
    =
    0.45
     busts
    0.42
    feels
    0.42
     esses
    0.41
     vectores
    0.41
    ystem
    0.41
    reve
    0.41
     emocional
    0.41
    POSITIVE LOGITS
     đích
    0.43
     আমাদের
    0.42
    Bennett
    0.42
    Aim
    0.41
     hän
    0.41
     Schmidt
    0.39
    Overlay
    0.39
    Cardiac
    0.39
     Coordinator
    0.39
    Stub
    0.38
    Act Density 0.026%

    No Known Activations