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

    Neuronpedia

    INDEX
    Explanations

    general discussion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (state
    -0.07
     х
    -0.07
    ерин
    -0.06
    parsers
    -0.06
    abol
    -0.06
    -u
    -0.06
    	redirect
    -0.06
    итов
    -0.06
    اطل
    -0.06
     Rigidbody
    -0.06
    POSITIVE LOGITS
     süt
    0.06
     Mrs
    0.06
     Primary
    0.06
     Si
    0.06
    Anim
    0.06
    AUTH
    0.06
     можете
    0.06
    "These
    0.06
    leaflet
    0.06
     Си
    0.06
    Act Density 0.188%

    No Known Activations