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

    Neuronpedia

    INDEX
    Explanations

    insertion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [len
    -0.07
     bigger
    -0.07
    ultipart
    -0.07
     יור
    -0.07
    淚
    -0.06
     tr
    -0.06
     לל
    -0.06
     foes
    -0.06
    three
    -0.06
    震动
    -0.06
    POSITIVE LOGITS
    gment
    0.08
    ража
    0.07
    chant
    0.07
     צריך
    0.07
    collection
    0.07
    机制
    0.07
    (assert
    0.06
    庄
    0.06
     Substance
    0.06
    щин
    0.06
    Act Density 0.003%

    No Known Activations