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

    Neuronpedia

    INDEX
    Explanations

    mandatory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    htu
    -0.08
     Planta
    -0.08
    ’entreprise
    -0.08
     esthétique
    -0.08
     kakhulu
    -0.07
    ütte
    -0.07
     aesthetics
    -0.07
     Erde
    -0.07
    kien
    -0.07
     circulating
    -0.07
    POSITIVE LOGITS
    _reduce
    0.09
     reductions
    0.09
     mandated
    0.08
     zwing
    0.08
     sentencing
    0.08
    _RULE
    0.08
     Rules
    0.08
     नियम
    0.08
     regras
    0.08
     Reduction
    0.08
    Act Density 0.005%

    No Known Activations