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

    Neuronpedia

    INDEX
    Explanations

    Financial reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تض
    -0.07
    Validation
    -0.07
    atching
    -0.07
     Prepare
    -0.07
    uggested
    -0.06
    leton
    -0.06
    Cut
    -0.06
     programmes
    -0.06
    Box
    -0.06
    Cars
    -0.06
    POSITIVE LOGITS
     gece
    0.07
     billig
    0.06
    해서
    0.06
    @register
    0.06
     запах
    0.06
    πουλος
    0.06
     대행
    0.06
     박
    0.06
    ]+'
    0.06
    seys
    0.06
    Act Density 0.012%

    No Known Activations