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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     linux
    -0.07
    νης
    -0.06
    λογ
    -0.06
    pq
    -0.06
    YS
    -0.06
     CG
    -0.06
    .write
    -0.06
     establishes
    -0.06
    ้าต
    -0.06
    Importer
    -0.06
    POSITIVE LOGITS
     böylece
    0.06
     Provision
    0.06
     svět
    0.06
    (Messages
    0.06
     şiddet
    0.06
     nội
    0.06
    (num
    0.06
    _valor
    0.06
    -question
    0.06
     دوباره
    0.06
    Act Density 0.025%

    No Known Activations