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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    primir
    -0.07
    .vertex
    -0.07
    PELL
    -0.07
    셴
    -0.07
    _che
    -0.07
     VOID
    -0.07
     spokesperson
    -0.07
    却又
    -0.07
     vive
    -0.07
     Faces
    -0.07
    POSITIVE LOGITS
    恍
    0.08
    -read
    0.08
    公里
    0.07
    乱
    0.07
    ..."
    0.07
    'an
    0.07
    🎛
    0.07
    yclic
    0.07
    かなり
    0.07
     declining
    0.07
    Act Density 0.012%

    No Known Activations