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

    Neuronpedia

    INDEX
    Explanations

    Objective Taking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لف
    0.39
    龙头
    0.39
    他说
    0.38
     canister
    0.38
     Örneğin
    0.38
     वृ
    0.37
    鳍
    0.37
    ंगी
    0.37
     কিন
    0.37
    jeć
    0.37
    POSITIVE LOGITS
     broaden
    0.42
    vamos
    0.39
     depictions
    0.39
     nasze
    0.39
     cooperate
    0.38
    辿
    0.37
    dummies
    0.36
     together
    0.36
     निश्चित
    0.36
     comply
    0.36
    Act Density 0.001%

    No Known Activations