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

    Neuronpedia

    INDEX
    Explanations

    Plural forms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /name
    -0.07
    Engine
    -0.06
    Comment
    -0.06
     wrapped
    -0.06
    خم
    -0.06
     nej
    -0.06
     workflow
    -0.06
    :])
    -0.06
    níkem
    -0.06
    HTTPHeader
    -0.06
    POSITIVE LOGITS
     disturbing
    0.07
    ije
    0.07
    �
    0.07
    finalize
    0.07
     인간
    0.06
    "One
    0.06
    	O
    0.06
     �
    0.06
     battles
    0.06
    owie
    0.06
    Act Density 0.405%

    No Known Activations