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

    Neuronpedia

    INDEX
    Explanations

    diagnosis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     commentary
    -0.09
     piping
    -0.08
     blueprint
    -0.08
     tradução
    -0.07
    让我
    -0.07
     Blueprint
    -0.07
     Kommentar
    -0.07
     ül
    -0.07
     lassen
    -0.07
     Macbeth
    -0.07
    POSITIVE LOGITS
     pruebas
    0.09
     acudir
    0.09
     definitive
    0.09
     подтверж
    0.09
     corrobor
    0.09
    доб
    0.08
     confirm
    0.08
    _confirm
    0.08
    ktf
    0.08
    (criteria
    0.08
    Act Density 0.015%

    No Known Activations