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

    Neuronpedia

    INDEX
    Explanations

    create action, an API

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Water
    0.48
    R
    0.47
     Br
    0.46
    is
    0.45
     ordination
    0.42
     Crem
    0.41
    Br
    0.39
     Muscle
    0.39
    all
    0.38
    "
    0.38
    POSITIVE LOGITS
     noqa
    0.48
    ദ്ധ
    0.44
    وجوان
    0.41
    ිබ
    0.41
    ，“
    0.40
    0.39
     öz
    0.39
     razón
    0.39
     lokalen
    0.39
    ྤ
    0.39
    Act Density 0.000%

    No Known Activations