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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Camera
    -0.07
     relevant
    -0.06
    児
    -0.06
     sequentially
    -0.06
     cops
    -0.06
    akukan
    -0.06
    umbles
    -0.06
    train
    -0.06
     behave
    -0.06
     Coy
    -0.06
    POSITIVE LOGITS
    ares
    0.07
    _cores
    0.07
    praak
    0.07
     tehlik
    0.07
     dohod
    0.07
    /////
    0.07
     DOWNLOAD
    0.06
     Fathers
    0.06
    /datatables
    0.06
    /music
    0.06
    Act Density 0.025%

    No Known Activations