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

    Neuronpedia

    INDEX
    Explanations

    scientific studies and research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chẳng
    -0.07
     agua
    -0.06
    ерш
    -0.06
    igkeit
    -0.06
     LZ
    -0.06
     ngon
    -0.06
     Σα
    -0.06
    uga
    -0.06
     ambos
    -0.05
     Filename
    -0.05
    POSITIVE LOGITS
     vědom
    0.07
    .Transform
    0.06
    Matthew
    0.06
    thritis
    0.06
    Workflow
    0.06
     ""},↵
    0.06
    ")
↵
    0.06
    $status
    0.06
     uplifting
    0.06
     parms
    0.06
    Act Density 0.053%

    No Known Activations