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

    Neuronpedia

    INDEX
    Explanations

    field

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Offensive
    -0.07
     Nodes
    -0.06
     Vienna
    -0.06
    ku
    -0.06
    ecta
    -0.06
     acknowledging
    -0.06
     palace
    -0.06
    dependence
    -0.06
     stocks
    -0.06
     Ro
    -0.06
    POSITIVE LOGITS
     zlep
    0.07
    .FAIL
    0.07
    Negative
    0.07
    apikey
    0.07
     Durant
    0.06
     Nous
    0.06
    reur
    0.06
     reporters
    0.06
    aleza
    0.06
    (jLabel
    0.06
    Act Density 0.011%

    No Known Activations