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

    Neuronpedia

    INDEX
    Explanations

    medical symptoms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     　　
    -0.08
     multin
    -0.06
    figur
    -0.06
    .dk
    -0.06
     doctoral
    -0.06
     insisted
    -0.06
     ]↵↵
    -0.06
     рис
    -0.06
    .employee
    -0.06
    ustomer
    -0.06
    POSITIVE LOGITS
    ARD
    0.07
     cin
    0.07
     우리
    0.07
     configparser
    0.07
    FOUND
    0.06
     Carpenter
    0.06
    _guid
    0.06
    먹
    0.06
    artisan
    0.06
     scenarios
    0.06
    Act Density 0.002%

    No Known Activations