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

    Neuronpedia

    INDEX
    Explanations

    specific examples for ML

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mögliche
    0.59
     vállalat
    0.57
     플러스
    0.55
     financi
    0.54
     politica
    0.53
     möglichen
    0.52
     posibles
    0.52
     secondi
    0.52
     posible
    0.51
     facteurs
    0.51
    POSITIVE LOGITS
    Introduction
    0.51
     Introduction
    0.49
     Instagram
    0.46
     It
    0.45
     Up
    0.45
    F
    0.44
     No
    0.43
    Observation
    0.43
     overheard
    0.42
    ↵
    0.42
    Act Density 0.001%

    No Known Activations