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

    Neuronpedia

    INDEX
    Explanations

    prior information and background

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     currently
    0.52
    目前
    0.52
     attualmente
    0.43
     past
    0.43
     Currently
    0.41
     former
    0.39
    過去
    0.39
     Lucas
    0.39
     formerly
    0.39
     Roger
    0.39
    POSITIVE LOGITS
     있던
    0.60
    knowledge
    0.42
     inhomogeneities
    0.42
    वर्ती
    0.41
    वार
    0.40
     znal
    0.40
    established
    0.40
     conocimientos
    0.39
    Cuál
    0.39
    uvad
    0.39
    Act Density 0.026%

    No Known Activations