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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PLAN
    -0.07
    せ
    -0.07
    iddle
    -0.06
     Houston
    -0.06
    الة
    -0.06
     που
    -0.06
     Said
    -0.06
     bird
    -0.06
     biçimde
    -0.06
     kw
    -0.06
    POSITIVE LOGITS
    >--}}↵
    0.07
     OC
    0.06
    	↵	↵
    0.06
     SceneManager
    0.06
     ""↵
    0.06
    .advance
    0.06
     Cartesian
    0.06
     garant
    0.06
    -backed
    0.06
    _cg
    0.06
    Act Density 0.134%

    No Known Activations