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

    Neuronpedia

    INDEX
    Explanations

    HTML tags

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     counselling
    -0.07
     Zh
    -0.07
     behand
    -0.07
    diamond
    -0.07
    男神
    -0.07
    Unhandled
    -0.07
     provisioning
    -0.07
     insisted
    -0.07
    _focus
    -0.07
     evid
    -0.07
    POSITIVE LOGITS
    ными
    0.07
    arbonate
    0.07
     metal
    0.07
    ному
    0.07
    uar
    0.07
    ного
    0.07
    ном
    0.07
    🖏
    0.06
    �
    0.06
    arkan
    0.06
    Act Density 0.011%

    No Known Activations