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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mov
    -0.08
     playbook
    -0.07
     decidedly
    -0.07
     encodeURIComponent
    -0.07
     Clifford
    -0.07
     oxide
    -0.07
    뉼
    -0.07
     nerve
    -0.07
     NEO
    -0.07
     nuevo
    -0.07
    POSITIVE LOGITS
     Walk
    0.07
    [i
    0.06
    青蛙
    0.06
    soles
    0.06
    toggle
    0.06
    .axis
    0.06
     *=
    0.06
     cakes
    0.06
    에
    0.06
    nable
    0.06
    Act Density 0.102%

    No Known Activations