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

    Neuronpedia

    INDEX
    Explanations

    interaction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Transcript
    -0.07
    ूज
    -0.06
     müm
    -0.06
    _fore
    -0.06
     ImVec
    -0.06
     حض
    -0.06
    PLEX
    -0.06
     fame
    -0.06
    )

↵
    -0.06
    )}"↵
    -0.06
    POSITIVE LOGITS
     weight
    0.07
     yu
    0.07
    itches
    0.07
     Serie
    0.06
     أث
    0.06
     communist
    0.06
    ั
    0.06
    �u
    0.06
     arr
    0.06
    =\"/
    0.06
    Act Density 0.006%

    No Known Activations