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

    Neuronpedia

    INDEX
    Explanations

    eagerly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -0.88
    ReusableCell
    -0.72
     Houſe
    -0.72
     itſelf
    -0.66
     myſelf
    -0.66
     houſe
    -0.66
     Monfieur
    -0.64
    wpi
    -0.63
    ſelf
    -0.63
     raiſ
    -0.63
    POSITIVE LOGITS
     import
    0.46
    ActionCreators
    0.44
     experiment
    0.44
    store
    0.43
    bre
    0.43
    悦
    0.42
    chtenstein
    0.42
    en
    0.41
    times
    0.41
    ubro
    0.40
    Act Density 0.006%

    No Known Activations