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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "testing
    -0.07
    _switch
    -0.07
    Of
    -0.07
     理
    -0.07
     Consulting
    -0.06
    Politics
    -0.06
     aşağıdaki
    -0.06
    	defer
    -0.06
     masturbation
    -0.06
    .libs
    -0.06
    POSITIVE LOGITS
     loginUser
    0.06
    ากาศ
    0.06
     transporter
    0.06
     srd
    0.06
     carousel
    0.06
     romance
    0.06
    LOGGER
    0.06
    RARY
    0.06
     visit
    0.06
    _permission
    0.06
    Act Density 0.023%

    No Known Activations