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

    Neuronpedia

    INDEX
    Explanations

    says

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     liber
    -0.08
     غني
    -0.08
    Cooldown
    -0.08
    gz
    -0.07
     инсп
    -0.07
    CY
    -0.07
    Liber
    -0.07
     просмотр
    -0.07
     griff
    -0.07
     Psychiatry
    -0.07
    POSITIVE LOGITS
     unclear
    0.10
     mention
    0.10
     unspecified
    0.09
     presumably
    0.09
     morphological
    0.09
     mentions
    0.08
     mentioning
    0.08
     bracket
    0.08
     disebut
    0.08
    ाक्ष
    0.08
    Act Density 0.168%

    No Known Activations