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

    Neuronpedia

    INDEX
    Explanations

    specific phrases with definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Estudios
    0.42
     Studio
    0.40
    acijama
    0.40
    öö
    0.39
    ਨੀ
    0.38
    isiä
    0.38
    itsyn
    0.38
     Appear
    0.38
    studio
    0.37
    voor
    0.37
    POSITIVE LOGITS
     అదే
    0.45
     each
    0.42
    შინ
    0.41
    ₲
    0.41
     ৬৬
    0.40
    Lone
    0.40
     हर
    0.40
     comics
    0.40
     tuck
    0.40
     reductions
    0.39
    Act Density 0.001%

    No Known Activations