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

    Neuronpedia

    INDEX
    Explanations

    spoiled

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diesel
    -0.09
     transitional
    -0.09
     sombre
    -0.08
     Collision
    -0.08
     daunting
    -0.08
     planos
    -0.08
     Burn
    -0.08
     transmissão
    -0.08
     prelim
    -0.08
     Transitional
    -0.08
    POSITIVE LOGITS
    呵
    0.11
    protected
    0.09
     nurturing
    0.09
     protects
    0.09
    0.09
     infantil
    0.08
     protected
    0.08
     praise
    0.08
    Protected
    0.08
     exces
    0.08
    Act Density 0.008%

    No Known Activations