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

    Neuronpedia

    INDEX
    Explanations

    code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .$\
    0.77
    ௫
    0.71
     microsomal
    0.71
    ύ
    0.70
     pptn
    0.69
     terrific
    0.67
     geochemical
    0.67
     pernicious
    0.66
    𝟘
    0.66
     cyclotron
    0.64
    POSITIVE LOGITS
    at
    0.66
    el
    0.65
    in
    0.63
    ↵
    0.61
     a
    0.58
    s
    0.57
     IDs
    0.56
     S
    0.55
     M
    0.55
    Main
    0.55
    Act Density 0.000%

    No Known Activations