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

    Neuronpedia

    INDEX
    Explanations

    golang code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ForgotPassword
    0.53
    ện
    0.46
    <unused283>
    0.45
     ወይም
    0.45
    Sustainability
    0.45
    불어
    0.44
    ParentElement
    0.44
     করতে
    0.44
    动脉
    0.43
    तया
    0.43
    POSITIVE LOGITS
    0.57
    ג
    0.41
     horses
    0.41
     isop
    0.40
     silicon
    0.40
    how
    0.38
     oils
    0.38
     on
    0.38
     beetle
    0.38
     exodus
    0.38
    Act Density 0.001%

    No Known Activations