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

    Neuronpedia

    INDEX
    Explanations

    itz

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    groups
    -0.08
    -es
    -0.07
    ecal
    -0.07
    Psy
    -0.06
     drums
    -0.06
     settlements
    -0.06
     ISS
    -0.06
    Risk
    -0.06
    -cr
    -0.06
    λμ
    -0.06
    POSITIVE LOGITS
     Holt
    0.07
     closeButton
    0.06
     fuller
    0.06
    -filled
    0.06
     Confirm
    0.06
     ・
    0.06
     HVAC
    0.06
     backstage
    0.06
    πη
    0.06
    _binary
    0.05
    Act Density 0.000%

    No Known Activations