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

    Neuronpedia

    INDEX
    Explanations

    ties and geometry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ties
    -2.42
     tie
    -2.31
    tie
    -2.28
    tied
    -1.98
     ties
    -1.96
     Tie
    -1.91
    Tie
    -1.90
     Ties
    -1.84
     tied
    -1.73
    TIE
    -1.64
    POSITIVE LOGITS
    t
    0.54
    iri
    0.53
    cheibe
    0.51
     Ferner
    0.49
    ed
    0.48
     Byd
    0.48
    ồm
    0.47
    i
    0.45
    voller
    0.45
    SPJ
    0.44
    Act Density 0.098%

    No Known Activations