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

    Neuronpedia

    INDEX
    Explanations

    ancer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ozy
    -0.07
    (ad
    -0.06
    .Sub
    -0.06
    vero
    -0.06
     活
    -0.06
    _ISS
    -0.06
    _AD
    -0.06
    ((_
    -0.06
    幕
    -0.06
     storytelling
    -0.06
    POSITIVE LOGITS
     Dustin
    0.07
     Hist
    0.06
     mutating
    0.06
     FSM
    0.06
    _literals
    0.06
     وصلات
    0.06
    camel
    0.06
    UDGE
    0.06
    роч
    0.06
    rb
    0.06
    Act Density 0.003%

    No Known Activations