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

    Neuronpedia

    INDEX
    Explanations

    content policy

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Policies
    1.60
    Policies
    1.52
     정책
    1.52
     policies
    1.51
    政策
    1.51
    policies
    1.39
    Policy
    1.38
     policy
    1.36
    정책
    1.36
     POLICY
    1.30
    POSITIVE LOGITS
     icy
    0.74
    iliy
    0.73
    cy
    0.70
    oley
    0.70
     po
    0.66
    iky
    0.66
    icin
    0.63
    icy
    0.62
    po
    0.61
    olic
    0.61
    Act Density 0.009%

    No Known Activations