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

    Neuronpedia

    INDEX
    Explanations

    fig

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     photon
    -0.08
    üst
    -0.07
     explain
    -0.07
     testify
    -0.07
     beyond
    -0.07
     benefit
    -0.07
     inline
    -0.07
    萩
    -0.07
    Boolean
    -0.07
     Travis
    -0.07
    POSITIVE LOGITS
     memorable
    0.08
    垡
    0.08
    (results
    0.07
    (figsize
    0.07
     [{↵
    0.07
    liers
    0.07
     �
    0.07
     Forms
    0.07
    ">$
    0.07
    标记
    0.07
    Act Density 0.001%

    No Known Activations