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

    Neuronpedia

    INDEX
    Explanations

    Instructions, processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _literal
    -0.06
     concentrating
    -0.06
     Sands
    -0.06
     solitary
    -0.06
    テ
    -0.06
    ij
    -0.05
    Prosec
    -0.05
    .browser
    -0.05
     promises
    -0.05
     hubs
    -0.05
    POSITIVE LOGITS
    adolu
    0.08
    ,output
    0.07
    ackbar
    0.07
    _EXIT
    0.07
    olución
    0.06
     twitter
    0.06
    Keeper
    0.06
     night
    0.06
    ieur
    0.06
    kiem
    0.06
    Act Density 0.044%

    No Known Activations