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

    Neuronpedia

    INDEX
    Explanations

    Throw

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     비교
    -0.07
    더
    -0.07
     clums
    -0.07
    Mount
    -0.06
    нош
    -0.06
    füg
    -0.06
     生命周期
    -0.06
     Fisher
    -0.06
     largely
    -0.06
     Mount
    -0.06
    POSITIVE LOGITS
    (grammar
    0.06
     comeback
    0.06
     admitting
    0.06
    (Person
    0.06
     �
    0.06
     Il
    0.06
     brag
    0.06
     irritating
    0.06
     dunk
    0.06
    instead
    0.06
    Act Density 0.124%

    No Known Activations