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

    Neuronpedia

    INDEX
    Explanations

    you're welcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tooth
    0.45
    Fang
    0.40
    itore
    0.40
    Yesterday
    0.40
    Speak
    0.39
    Town
    0.39
    你们
    0.38
    onn
    0.38
    cias
    0.38
    Iam
    0.37
    POSITIVE LOGITS
     воло
    0.44
     gone
    0.41
     ባህ
    0.41
    </strong>
    0.39
    POSTFIELDS
    0.37
    }\|\
    0.36
    }+...+\
    0.36
    面倒
    0.36
     ultraviolet
    0.35
    ಗೆ
    0.35
    Act Density 0.004%

    No Known Activations