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

    Neuronpedia

    INDEX
    Explanations

    Staying focused

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     เท
    -0.08
     चुन
    -0.08
     cookware
    -0.07
     MET
    -0.07
     _)
    -0.07
     Edu
    -0.07
     tegen
    -0.07
     opmerkingen
    -0.07
     latin
    -0.07
    体育
    -0.07
    POSITIVE LOGITS
     direcion
    0.12
     방향
    0.12
    direction
    0.11
     दिशा
    0.11
    Direction
    0.11
     purposeful
    0.11
    方向
    0.11
     direction
    0.11
     목적
    0.10
     목표
    0.10
    Act Density 0.039%

    No Known Activations