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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     discount
    -0.06
    (sock
    -0.06
    illow
    -0.06
    ach
    -0.06
    uforia
    -0.06
    ANA
    -0.06
     فول
    -0.05
    <Address
    -0.05
     yen
    -0.05
     cable
    -0.05
    POSITIVE LOGITS
     tumult
    0.07
     tienen
    0.07
     templ
    0.06
     brushing
    0.06
     поступ
    0.06
    =train
    0.06
     Toplam
    0.06
    hou
    0.06
    /Instruction
    0.06
     současné
    0.06
    Act Density 0.272%

    No Known Activations