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

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     серед
    -0.07
     fullPath
    -0.07
    -minus
    -0.07
    Imm
    -0.06
     Stim
    -0.06
     realizar
    -0.06
    �
    -0.06
     Μα
    -0.06
    snap
    -0.06
    izziness
    -0.06
    POSITIVE LOGITS
    _checker
    0.07
    erialized
    0.06
     appeared
    0.06
    (|
    0.06
     angry
    0.06
    比赛
    0.06
     jm
    0.06
    .th
    0.06
     Broadcast
    0.06
    709
    0.06
    Act Density 0.025%

    No Known Activations