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

    Neuronpedia

    INDEX
    Explanations

    Spencer, material, format, range, (

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     изначально
    0.36
     microbiome
    0.34
    ⤷
    0.34
    0.33
     mudanças
    0.33
    ய்டா
    0.33
    0.33
     onboarding
    0.33
     timeline
    0.33
    ലിം
    0.32
    POSITIVE LOGITS
     apparatus
    0.33
    tf
    0.31
    f
    0.29
    for
    0.29
    of
    0.29
    device
    0.29
    tor
    0.28
     device
    0.27
    or
    0.27
    tn
    0.27
    Act Density 0.000%

    No Known Activations