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

    Neuronpedia

    INDEX
    Explanations

    violates my policy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    前
    0.39
     //{
    0.38
    穴
    0.37
     isomorphic
    0.36
    DataAnnotations
    0.35
    DEBUG
    0.35
     evanescent
    0.35
     sqlType
    0.35
     HOMO
    0.34
    뗄
    0.34
    POSITIVE LOGITS
     policy
    1.52
    Policy
    1.39
     policies
    1.38
    政策
    1.38
    policy
    1.36
     정책
    1.34
     Policy
    1.32
    ポリシー
    1.26
     Policies
    1.24
     POLICY
    1.21
    Act Density 0.225%

    No Known Activations