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

    Neuronpedia

    INDEX
    Explanations

    question marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lite
    -0.07
     gathered
    -0.07
     Highway
    -0.06
     Dock
    -0.06
    Airport
    -0.06
     docking
    -0.06
    Gun
    -0.06
     فرو
    -0.06
    落
    -0.06
    798
    -0.06
    POSITIVE LOGITS
    -email
    0.07
    vably
    0.07
    .semantic
    0.07
    ��
    0.06
    rst
    0.06
    phins
    0.06
     substitution
    0.06
     '".
    0.06
    ichern
    0.06
    =pk
    0.06
    Act Density 0.002%

    No Known Activations