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

    Neuronpedia

    INDEX
    Explanations

    KIND

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ram
    -0.08
     blow
    -0.07
    .Acc
    -0.07
     schemes
    -0.07
    Psi
    -0.06
    σπ
    -0.06
    "W
    -0.06
     �
    -0.06
     Rewards
    -0.06
    	option
    -0.06
    POSITIVE LOGITS
    atis
    0.06
    /graphql
    0.06
    cup
    0.06
     taxed
    0.06
     pier
    0.06
    $client
    0.06
     dial
    0.06
    -invalid
    0.06
    надлеж
    0.06
    _checkout
    0.06
    Act Density 0.002%

    No Known Activations