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

    Neuronpedia

    INDEX
    Explanations

    cords, ropes, hoses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (factory
    -0.06
    Animated
    -0.06
     katıl
    -0.06
    燃
    -0.06
    :right
    -0.06
     처
    -0.05
     Comedy
    -0.05
    ory
    -0.05
    _friend
    -0.05
     Jong
    -0.05
    POSITIVE LOGITS
     specification
    0.07
     आन
    0.07
    bsub
    0.07
     list
    0.07
    ologia
    0.06
    (ib
    0.06
     ей
    0.06
    Pin
    0.06
    Call
    0.06
    -regexp
    0.06
    Act Density 0.035%

    No Known Activations