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

    Neuronpedia

    INDEX
    Explanations

    names in academic contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pension
    0.50
    घाडी
    0.48
     TripAdvisor
    0.47
    Bankruptcy
    0.47
    जारत
    0.46
    ğinden
    0.46
    entertainment
    0.44
     Букмекердик
    0.44
     आवाहन
    0.44
    👥
    0.44
    POSITIVE LOGITS
    _
    0.56
     vertex
    0.51
     quiescent
    0.49
     lectures
    0.47
    {
    0.47
     undergrad
    0.46
     undergraduate
    0.46
    @
    0.45
     ∈
    0.45
     arXiv
    0.44
    Act Density 0.001%

    No Known Activations