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

    Neuronpedia

    INDEX
    Explanations

    Vector Network

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    U
    0.90
     Audience
    0.86
    Appl
    0.84
    Å
    0.84
     Nutzer
    0.83
     Área
    0.83
    jed
    0.80
     Adaptive
    0.78
    N
    0.78
     Enseñanza
    0.78
    POSITIVE LOGITS
     conquered
    0.72
     fabricants
    0.68
    犸
    0.68
    ᱼ
    0.66
     carène
    0.65
    ังหว
    0.64
     soared
    0.64
     tormented
    0.64
    राना
    0.63
    斯拉
    0.62
    Act Density 0.533%

    No Known Activations