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
    ้
    -0.07
     Ε
    -0.06
    _dark
    -0.06
     Outlook
    -0.06
     것을
    -0.06
    beros
    -0.06
     elite
    -0.06
    (light
    -0.06
     enroll
    -0.06
    dim
    -0.06
    POSITIVE LOGITS
    acak
    0.07
    �
    0.06
    appers
    0.06
    .tab
    0.06
    "]."
    0.06
    .ItemsSource
    0.06
     Stam
    0.06
     olabilir
    0.06
     earthquake
    0.06
    malı
    0.06
    Act Density 0.031%

    No Known Activations