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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icted
    -0.06
     sprinkle
    -0.06
     founder
    -0.06
     العق
    -0.06
    ात
    -0.06
     reef
    -0.06
    dad
    -0.06
    rip
    -0.06
    Leaders
    -0.06
     fondo
    -0.06
    POSITIVE LOGITS
    ">\
    0.07
    .datatables
    0.06
    .keywords
    0.06
    ::::::::::::::::::::::::::::::::
    0.06
     illustrate
    0.06
     contrato
    0.06
     başlan
    0.06
    しまった
    0.06
     протяж
    0.06
    \Models
    0.06
    Act Density 0.005%

    No Known Activations