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

    Neuronpedia

    INDEX
    Explanations

    signal-to-noise ratio

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _TOOL
    -0.07
     Worksheet
    -0.07
    แทน
    -0.07
    ordes
    -0.06
    _disconnect
    -0.06
    .CG
    -0.06
     pois
    -0.06
     Yug
    -0.06
    tls
    -0.06
     weil
    -0.06
    POSITIVE LOGITS
     strán
    0.06
    /'↵↵
    0.06
     bank
    0.06
     managerial
    0.06
     фінанс
    0.06
     nutrit
    0.06
     nokt
    0.06
     unlikely
    0.06
     township
    0.06
    ancements
    0.06
    Act Density 0.004%

    No Known Activations