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

    Neuronpedia

    INDEX
    Explanations

    ou

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (am
    -0.07
     preamble
    -0.07
    jay
    -0.06
    芬
    -0.06
    former
    -0.06
    .program
    -0.06
    -orange
    -0.06
     meş
    -0.06
     proved
    -0.06
     coordinator
    -0.06
    POSITIVE LOGITS
    _WH
    0.07
    �
    0.07
     Newly
    0.07
    Array
    0.07
    .bin
    0.06
    Loc
    0.06
    bufio
    0.06
    (GLFW
    0.06
     pairs
    0.06
    ConnectionFactory
    0.06
    Act Density 0.000%

    No Known Activations