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

    Neuronpedia

    INDEX
    Explanations

    Hearing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     provisioning
    -0.06
    tas
    -0.06
    reading
    -0.06
    Una
    -0.06
     мов
    -0.06
    ovaných
    -0.06
    efd
    -0.06
    iane
    -0.06
    entes
    -0.06
     hs
    -0.06
    POSITIVE LOGITS
    　V
    0.07
    -expand
    0.07
    /env
    0.07
    0.06
     المملكة
    0.06
     学
    0.06
    0.06
    爆
    0.06
    0.06
    	first
    0.06
    Act Density 0.029%

    No Known Activations