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

    Neuronpedia

    INDEX
    Explanations

    goals and topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нок
    0.53
    रा
    0.49
    consider
    0.49
    い
    0.47
    chromium
    0.47
    ococcus
    0.46
    alc
    0.46
    coherent
    0.46
    remember
    0.46
    remark
    0.45
    POSITIVE LOGITS
     Fishing
    0.48
     చేప
    0.46
     Film
    0.45
     Drei
    0.44
     Goals
    0.43
    Fishing
    0.43
     เป้า
    0.43
     ലീ
    0.43
     Ziel
    0.42
     filme
    0.42
    Act Density 0.006%

    No Known Activations