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

    Neuronpedia

    INDEX
    Explanations

    academic papers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     தினம்
    0.36
     ලැබ
    0.36
     食器
    0.35
    явления
    0.35
     ३
    0.35
     consta
    0.34
     compreensão
    0.34
     見
    0.34
     нәрсә
    0.34
     служба
    0.34
    POSITIVE LOGITS
    P
    0.40
    O
    0.37
    Q
    0.35
    G
    0.34
    Př
    0.33
    ید
    0.33
    ಬ್
    0.33
    African
    0.32
    V
    0.32
    ad
    0.31
    Act Density 0.612%

    No Known Activations