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

    Neuronpedia

    INDEX
    Explanations

    derivatives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ece
    -0.07
    یان
    -0.07
    ادث
    -0.07
    ên
    -0.06
     zoekt
    -0.06
    LOCK
    -0.06
    	top
    -0.06
    ิมพ
    -0.06
    رود
    -0.06
    ić
    -0.06
    POSITIVE LOGITS
     rub
    0.06
     enroll
    0.06
     weight
    0.06
     pastors
    0.06
     Nikol
    0.06
    Club
    0.06
    sq
    0.06
     ruler
    0.06
    pherical
    0.06
     stran
    0.06
    Act Density 0.001%

    No Known Activations