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

    Neuronpedia

    INDEX
    Explanations

    across

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     across
    -1.71
    across
    -1.54
     Across
    -1.46
    Across
    -1.33
     ACROSS
    -1.29
     nationwide
    -0.88
     statewide
    -0.83
     varandra
    -0.77
     imprimée
    -0.77
     worldwide
    -0.71
    POSITIVE LOGITS
     the
    0.68
    #![
    0.55
     pe
    0.48
     dich
    0.47
    overs
    0.46
     pris
    0.46
     onAnimation
    0.45
     a
    0.44
     super
    0.44
     par
    0.44
    Act Density 0.127%

    No Known Activations