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

    Neuronpedia

    INDEX
    Explanations

    morality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SPA
    -0.06
     lament
    -0.06
     bunker
    -0.06
     ιστο
    -0.06
     PRIV
    -0.06
    _nc
    -0.06
    _RS
    -0.05
     आए
    -0.05
     ánh
    -0.05
    %，
    -0.05
    POSITIVE LOGITS
     morality
    0.14
    ether
    0.07
    onto
    0.07
     Primer
    0.07
    ->$
    0.07
    vore
    0.07
    面積
    0.07
     validator
    0.07
    Wallet
    0.07
     Authentic
    0.06
    Act Density 0.004%

    No Known Activations