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

    Neuronpedia

    INDEX
    Explanations

    sides of an argument

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    %),
    -0.06
     FIT
    -0.06
     Jail
    -0.06
    üsü
    -0.06
    ایند
    -0.06
     radiator
    -0.05
    Characteristic
    -0.05
    یف
    -0.05
    lei
    -0.05
    ird
    -0.05
    POSITIVE LOGITS
    Dealer
    0.07
    681
    0.07
     UIAlertView
    0.06
     FullName
    0.06
     Note
    0.06
     bronze
    0.06
    apollo
    0.06
     kulak
    0.06
    -outline
    0.06
     comp
    0.06
    Act Density 0.014%

    No Known Activations