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

    Neuronpedia

    INDEX
    Explanations

    [in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -details
    -0.09
     HEX
    -0.06
     streams
    -0.06
     =================================================================================
    -0.06
    ojis
    -0.06
     наслід
    -0.06
    지막
    -0.06
     Пот
    -0.06
    FONT
    -0.06
    rozen
    -0.06
    POSITIVE LOGITS
    [in
    0.09
    [from
    0.07
     controlled
    0.06
     nag
    0.06
     wagon
    0.06
     Medal
    0.06
    :create
    0.06
     Controlled
    0.06
    Martin
    0.06
     мед
    0.06
    Act Density 0.000%

    No Known Activations