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

    Neuronpedia

    INDEX
    Explanations

    stars and capital

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cardigan
    -0.08
     fria
    -0.08
     mitochond
    -0.08
     Fox
    -0.07
     susceptible
    -0.07
     favorable
    -0.07
    igue
    -0.07
    需
    -0.07
     weary
    -0.07
    nickname
    -0.07
    POSITIVE LOGITS
     desconoc
    0.08
     schön
    0.08
     personagem
    0.07
    (square
    0.07
    Condition
    0.07
     onboarding
    0.07
    Character
    0.07
     sata
    0.07
    .Final
    0.07
    STATE
    0.07
    Act Density 0.001%

    No Known Activations