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

    Neuronpedia

    INDEX
    Explanations

    technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >In
    -0.07
    .fore
    -0.07
     On
    -0.07
     in
    -0.07
     For
    -0.06
     từ
    -0.06
    setter
    -0.06
     on
    -0.06
    vet
    -0.06
     للإ
    -0.06
    POSITIVE LOGITS
     figure
    0.07
    _epi
    0.06
    ↵↵↵↵
    0.06
     #"
    0.06
    ↵↵↵
    0.06
    TRL
    0.06
    ुध
    0.06
    аст
    0.06
    ****
    0.06
    engl
    0.06
    Act Density 0.329%

    No Known Activations