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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ti
    -0.07
    �
    -0.07
    .Bit
    -0.07
    追逐
    -0.07
    istro
    -0.07
    bus
    -0.07
    Check
    -0.07
    /text
    -0.06
    NOT
    -0.06
    goto
    -0.06
    POSITIVE LOGITS
     clipped
    0.07
     mik
    0.07
     explan
    0.07
    냵
    0.07
     unlocks
    0.07
    alık
    0.07
    🦌
    0.07
     roaring
    0.07
     собак
    0.06
    🏛
    0.06
    Act Density 0.002%

    No Known Activations