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

    Neuronpedia

    INDEX
    Explanations

    file not found errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Exit
    0.42
     ug
    0.41
     Exit
    0.40
    throw
    0.40
    oral
    0.39
    ক
    0.39
     E
    0.38
     throw
    0.38
    ember
    0.38
    bling
    0.37
    POSITIVE LOGITS
     Prac
    0.38
     infrac
    0.37
    jegyz
    0.37
    ныя
    0.37
    زيز
    0.36
     poised
    0.36
     पटाखे
    0.36
     बच्‍
    0.36
    りは
    0.35
    に関連
    0.35
    Act Density 0.001%

    No Known Activations