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

    Neuronpedia

    INDEX
    Explanations

    technical/formal text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Поч
    -0.08
     زند
    -0.06
    HANDLE
    -0.06
     вина
    -0.06
    孙
    -0.06
    );$
    -0.06
    ophy
    -0.06
     sincerity
    -0.06
     Benefits
    -0.06
     نیر
    -0.06
    POSITIVE LOGITS
    -tr
    0.07
    Club
    0.07
    842
    0.06
     Prices
    0.06
    Spec
    0.06
    Unt
    0.06
    						↵
    0.06
    formation
    0.06
    lab
    0.06
     pep
    0.06
    Act Density 0.000%

    No Known Activations