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

    Neuronpedia

    INDEX
    Explanations

    llications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ``(
    -0.08
    agnetic
    -0.07
     Queue
    -0.06
    aki
    -0.06
     Modules
    -0.06
    パン
    -0.06
    _car
    -0.06
    ulus
    -0.06
     lớp
    -0.06
    aways
    -0.06
    POSITIVE LOGITS
     presidency
    0.07
     Stealth
    0.07
    Thunk
    0.06
     physique
    0.06
     ikinci
    0.06
     движ
    0.06
    PAY
    0.06
     indie
    0.06
    840
    0.06
     largo
    0.06
    Act Density 0.001%

    No Known Activations