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
     ถ
    -0.07
     Gala
    -0.07
     kiện
    -0.07
     difficulties
    -0.07
     occupy
    -0.07
    .Tools
    -0.06
     Clintons
    -0.06
     πρό
    -0.06
    	des
    -0.06
     αλλά
    -0.06
    POSITIVE LOGITS
    IFIED
    0.06
    าญ
    0.06
    ITIONS
    0.06
    Modified
    0.06
     Norris
    0.06
    IDER
    0.06
    ulse
    0.06
     pulse
    0.06
     Processor
    0.06
    stderr
    0.06
    Act Density 0.000%

    No Known Activations