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

    Neuronpedia

    INDEX
    Explanations

    ir

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    袖
    -0.07
     buddy
    -0.07
     WELL
    -0.07
     Над
    -0.07
    .ObjectMapper
    -0.06
    inch
    -0.06
    _seq
    -0.06
    版本
    -0.06
    -0.06
    UNCH
    -0.06
    POSITIVE LOGITS
     Hir
    0.24
     Kir
    0.14
    irsch
    0.12
    hir
    0.12
    Kir
    0.11
    HIR
    0.11
     Gir
    0.10
     Shir
    0.10
     kir
    0.10
    ir
    0.09
    Act Density 0.007%

    No Known Activations