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

    Neuronpedia

    INDEX
    Explanations

    code and markup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ALOG
    -0.07
     misunder
    -0.07
    ，本
    -0.06
     accomplish
    -0.06
     LLVM
    -0.06
    maktadır
    -0.06
    ψης
    -0.06
     Alb
    -0.06
    лара
    -0.06
    arefa
    -0.06
    POSITIVE LOGITS
     flashlight
    0.07
    fighter
    0.06
     ],
    0.06
    EDIA
    0.06
    ioneer
    0.06
    PyObject
    0.06
    على
    0.06
    Philip
    0.06
     ]
    0.06
    hil
    0.06
    Act Density 0.085%

    No Known Activations