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

    Neuronpedia

    INDEX
    Explanations

    personal views

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Polynomial
    0.45
     〢
    0.44
    步骤
    0.44
    ྭ
    0.44
    ায
    0.42
    Improvements
    0.42
     Steps
    0.42
     Technique
    0.42
    用到
    0.42
    র্
    0.41
    POSITIVE LOGITS
     beliefs
    2.41
     attitudes
    2.17
    beliefs
    2.06
     opinions
    1.93
     perceptions
    1.91
     viewpoints
    1.84
     worldview
    1.82
     belief
    1.80
     preferences
    1.80
     ideologies
    1.78
    Act Density 1.029%

    No Known Activations