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

    Neuronpedia

    INDEX
    Explanations

    -free

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    但这
    -0.07
     roofs
    -0.07
    }↵↵↵↵↵↵
    -0.07
    uron
    -0.07
     finishes
    -0.07
    esehen
    -0.06
     Bone
    -0.06
    白癜风
    -0.06
     BLOCK
    -0.06
    MAN
    -0.06
    POSITIVE LOGITS
    semantic
    0.07
    新た
    0.07
     thỏa
    0.07
     merely
    0.07
     bibli
    0.07
     necess
    0.06
    咏
    0.06
    EVER
    0.06
    agedList
    0.06
     הג
    0.06
    Act Density 0.853%

    No Known Activations