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

    Neuronpedia

    INDEX
    Explanations

    consequential

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zijn
    -0.07
     bleak
    -0.07
     ℝ
    -0.07
     Trib
    -0.06
    ่าม
    -0.06
    tls
    -0.06
    нил
    -0.06
    -opacity
    -0.06
    ूद
    -0.06
    фік
    -0.06
    POSITIVE LOGITS
    =%
    0.06
     ratified
    0.06
    vester
    0.06
     tap
    0.06
     contrace
    0.06
    ricane
    0.06
    VEST
    0.06
     千
    0.05
    OUGH
    0.05
     uf
    0.05
    Act Density 0.000%

    No Known Activations