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

    Neuronpedia

    INDEX
    Explanations

    Scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olars
    -0.07
    _build
    -0.06
     newUser
    -0.06
     کوه
    -0.06
     Gu
    -0.06
     evacuation
    -0.06
     histories
    -0.06
    	Double
    -0.06
    uang
    -0.06
     hoses
    -0.06
    POSITIVE LOGITS
     accelerated
    0.07
     ESPN
    0.07
    UREMENT
    0.07
    dej
    0.07
     Exc
    0.06
    ertime
    0.06
    aceutical
    0.06
    hp
    0.06
    nou
    0.06
    inou
    0.06
    Act Density 0.066%

    No Known Activations