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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Calculation
    -0.07
    .mapping
    -0.07
     calculating
    -0.07
    -row
    -0.06
    -foot
    -0.06
    小时
    -0.06
    itar
    -0.06
    -services
    -0.06
     telecom
    -0.06
     Patrick
    -0.06
    POSITIVE LOGITS
     Credit
    0.06
    'nun
    0.06
     (*.
    0.06
    .legend
    0.06
    プレ
    0.06
     보호
    0.06
     dzie
    0.06
     نقش
    0.06
    rott
    0.06
     плат
    0.06
    Act Density 0.054%

    No Known Activations