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

    Neuronpedia

    INDEX
    Explanations

    FK

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    аніз
    -0.06
    exampleInput
    -0.06
    _accuracy
    -0.06
    	Document
    -0.06
     ochran
    -0.06
    PasswordEncoder
    -0.06
    *dx
    -0.06
     náklad
    -0.06
    ιστο
    -0.05
     tolerance
    -0.05
    POSITIVE LOGITS
     Fort
    0.07
     abusing
    0.07
    ẩu
    0.06
    OptionsItemSelected
    0.06
     پا
    0.06
     wes
    0.06
     drive
    0.06
    انیا
    0.06
     tedious
    0.06
    امه
    0.06
    Act Density 0.003%

    No Known Activations