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

    Neuronpedia

    INDEX
    Explanations

    Happ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
    -0.76
     I
    -0.69
     '
    -0.61
     B
    -0.60
     N
    -0.57
     C
    -0.56
     O
    -0.56
     "
    -0.56
     H
    -0.55
     of
    -0.54
    POSITIVE LOGITS
     Efq
    1.54
     Monfieur
    1.54
     itſelf
    1.53
     Theſe
    1.40
     myſelf
    1.40
     $_"
    1.35
     poffible
    1.34
     Jefus
    1.34
     ་་
    1.30
     crdi
    1.30
    Act Density 1.326%

    No Known Activations