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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     (('
    -0.07
     Whale
    -0.06
     nt
    -0.06
    folios
    -0.06
    inite
    -0.06
     NodeType
    -0.06
     дитини
    -0.06
    parseInt
    -0.06
    oo
    -0.06
    @\
    -0.06
    POSITIVE LOGITS
     єв
    0.07
     discusses
    0.06
     gek
    0.06
    测试
    0.06
    .ecore
    0.06
    λα
    0.06
    olver
    0.06
     listed
    0.06
     south
    0.06
     yana
    0.06
    Act Density 0.005%

    No Known Activations