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

    Neuronpedia

    INDEX
    Explanations

    hash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itle
    -0.08
     "\"
    -0.07
    @GeneratedValue
    -0.07
    归属
    -0.07
    unfold
    -0.07
    ҷ
    -0.07
     mediante
    -0.07
    ensen
    -0.07
    "@
    -0.07
    截图
    -0.07
    POSITIVE LOGITS
    -go
    0.07
     bags
    0.07
    Features
    0.07
     bloom
    0.06
     Grat
    0.06
     naughty
    0.06
     stuck
    0.06
     keys
    0.06
     smoker
    0.06
    scious
    0.06
    Act Density 0.005%

    No Known Activations