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

    Neuronpedia

    INDEX
    Explanations

    These

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _fault
    -0.07
     capit
    -0.07
    ôt
    -0.07
     stif
    -0.06
    -vector
    -0.06
    llu
    -0.06
    _fg
    -0.06
    _pas
    -0.06
    AAA
    -0.06
     wiring
    -0.06
    POSITIVE LOGITS
     these
    0.21
     These
    0.18
    These
    0.13
    these
    0.13
    “These
    0.11
     THESE
    0.10
    "These
    0.10
     questi
    0.08
     Эти
    0.07
     Є
    0.07
    Act Density 0.065%

    No Known Activations