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
    itics
    -0.07
    .win
    -0.07
     üy
    -0.06
    ();

↵
    -0.06
    ong
    -0.06
    kie
    -0.06
    InputChange
    -0.06
    hello
    -0.06
    elong
    -0.06
    نین
    -0.06
    POSITIVE LOGITS
    [S
    0.07
    .CompareTo
    0.07
    oji
    0.06
     prostřednictvím
    0.06
     ساعت
    0.06
     �
    0.06
     nylon
    0.06
     Tiểu
    0.06
     Instruction
    0.06
     HH
    0.06
    Act Density 0.000%

    No Known Activations