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

    Neuronpedia

    INDEX
    Explanations

    guide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     internals
    -0.06
     pope
    -0.06
    IXEL
    -0.06
    .gt
    -0.06
     alc
    -0.06
    .But
    -0.06
    "Why
    -0.05
     feat
    -0.05
     fun
    -0.05
     SUV
    -0.05
    POSITIVE LOGITS
    ，同时
    0.07
     hairs
    0.07
     Thornton
    0.07
    -aligned
    0.07
    ItemType
    0.06
    saldo
    0.06
    sworth
    0.06
    IRST
    0.06
     princes
    0.06
    การส
    0.06
    Act Density 0.011%

    No Known Activations