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

    Neuronpedia

    INDEX
    Explanations

    100

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bree
    -0.07
     �
    -0.07
    vue
    -0.07
     Bike
    -0.07
    vec
    -0.07
     cha
    -0.07
    burst
    -0.07
    _decode
    -0.06
     bike
    -0.06
    áků
    -0.06
    POSITIVE LOGITS
    100
    0.13
    ){
↵
    0.07
    -INF
    0.07
    ↵
    0.07
    102
    0.07
     %↵
    0.07
    Support
    0.07
    140
    0.07
    160
    0.07
    Work
    0.07
    Act Density 0.051%

    No Known Activations