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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ㈣
    0.60
     pass
    0.59
    allen
    0.59
    ipation
    0.59
    integration
    0.58
    ímos
    0.58
    anaan
    0.58
    rschein
    0.56
    arum
    0.56
    anyon
    0.56
    POSITIVE LOGITS
    lines
    0.86
     Critic
    0.84
    l
    0.83
    Tick
    0.83
     Exams
    0.82
     Informe
    0.82
     Usuarios
    0.82
    t
    0.82
     Makeup
    0.81
     Tick
    0.81
    Act Density 0.000%

    No Known Activations