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

    Neuronpedia

    INDEX
    Explanations

    say ".Read" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     specifying
    -0.07
     Acres
    -0.07
     cname
    -0.07
    ewriter
    -0.06
     skateboard
    -0.06
    cloak
    -0.06
     спас
    -0.06
    lere
    -0.06
     ferm
    -0.06
    amientos
    -0.06
    POSITIVE LOGITS
     Delegate
    0.06
     Peer
    0.06
     Bridge
    0.06
     hungry
    0.06
    シ
    0.06
    develop
    0.06
     가족
    0.06
    .chart
    0.06
    DELAY
    0.06
    licting
    0.06
    Act Density 0.001%

    No Known Activations