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

    Neuronpedia

    INDEX
    Explanations

    stack up, set up, follow up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ategorie
    0.30
    Hz
    0.29
    Am
    0.28
    Arm
    0.28
    ms
    0.28
    ruption
    0.27
    sse
    0.27
    am
    0.27
    творення
    0.27
    Bin
    0.27
    POSITIVE LOGITS
    <unused2153>
    0.28
     wɔ
    0.27
     nhưng
    0.27
     endoplasmic
    0.25
     backstage
    0.25
     semelh
    0.25
     afield
    0.25
     क्योंकि
    0.25
     tonight
    0.25
     citiz
    0.25
    Act Density 0.029%

    No Known Activations