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

    Neuronpedia

    INDEX
    Explanations

    .com

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     malt
    -0.07
    (lr
    -0.07
     novamente
    -0.06
    pose
    -0.06
    ONLY
    -0.06
    琴
    -0.06
    ادل
    -0.06
    add
    -0.06
    ulia
    -0.06
    精品
    -0.06
    POSITIVE LOGITS
     �
    0.06
    sandbox
    0.06
    .Sql
    0.06
    models
    0.06
    の中
    0.06
     Nichols
    0.06
     futures
    0.06
     คล
    0.06
    кап
    0.06
     PRIV
    0.06
    Act Density 0.055%

    No Known Activations