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

    Neuronpedia

    INDEX
    Explanations

    legal non-compliance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Negra
    -0.09
    .Random
    -0.08
     Potential
    -0.08
    fragt
    -0.08
    UNIC
    -0.08
    ležit
    -0.08
     Toutes
    -0.08
     Bö
    -0.08
     Freitag
    -0.07
     potenci
    -0.07
    POSITIVE LOGITS
     incum
    0.11
     penalties
    0.11
    -payment
    0.10
     délais
    0.10
    Payment
    0.10
    付款
    0.10
    _payment
    0.09
    Mater
    0.09
    Penalty
    0.09
     penal
    0.09
    Act Density 0.020%

    No Known Activations