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

    Neuronpedia

    INDEX
    Explanations

    Technical writing fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nob
    -0.08
    Layout
    -0.07
     будто
    -0.06
    ству
    -0.06
    nb
    -0.06
     acknowledging
    -0.06
    фор
    -0.06
     childcare
    -0.06
    �
    -0.06
     HomeController
    -0.06
    POSITIVE LOGITS
    .']
    0.06
     označ
    0.06
    (cancel
    0.06
     (%
    0.06
     ErrorCode
    0.06
    (J
    0.05
     LE
    0.05
     Lanc
    0.05
     😉
    0.05
    fans
    0.05
    Act Density 0.001%

    No Known Activations