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

    Neuronpedia

    INDEX
    Explanations

    driven by, past -, allows for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NTFS
    0.51
     lantai
    0.48
    ک
    0.46
     considérons
    0.45
    대
    0.45
     Cortés
    0.44
    Municipio
    0.44
     luc
    0.43
    കോ
    0.43
     étoile
    0.43
    POSITIVE LOGITS
    in
    0.68
    svg
    0.57
    arq
    0.54
    皚
    0.53
    enburg
    0.49
    arXiv
    0.48
    faq
    0.48
    postal
    0.47
    nV
    0.46
     సాం
    0.45
    Act Density 0.012%

    No Known Activations