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

    Neuronpedia

    INDEX
    Explanations

    Karl Popper's philosophy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inscrições
    -0.08
    legacy
    -0.08
     biling
    -0.08
    册
    -0.08
     сох
    -0.08
     铭
    -0.08
    期开
    -0.08
     подар
    -0.08
     gifting
    -0.08
     баб
    -0.08
    POSITIVE LOGITS
     fals
    0.11
     hypotheses
    0.11
     hypothesis
    0.10
     Refin
    0.09
     refining
    0.09
     corrobor
    0.09
     dispro
    0.09
     വിമ
    0.09
     refined
    0.08
     Evidence
    0.08
    Act Density 0.015%

    No Known Activations