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

    Neuronpedia

    INDEX
    Explanations

    inappropriate/improper

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -site
    -0.07
     taxp
    -0.07
     devices
    -0.06
     ATTACK
    -0.06
     glossy
    -0.06
    .Dis
    -0.06
     Environment
    -0.06
     Nos
    -0.06
     Dis
    -0.06
     Constraint
    -0.06
    POSITIVE LOGITS
    vidence
    0.07
    elerik
    0.06
    ために
    0.06
    θυν
    0.06
     Dangerous
    0.06
     pudo
    0.06
    위를
    0.06
    koliv
    0.06
    ิทธ
    0.06
     Olymp
    0.06
    Act Density 0.054%

    No Known Activations