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

    Neuronpedia

    INDEX
    Explanations

    18

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amanho
    -0.07
    _attack
    -0.06
    customer
    -0.06
     متعدد
    -0.06
    _root
    -0.06
    (ship
    -0.06
     constructions
    -0.06
    Reduc
    -0.06
    .attachment
    -0.06
    -0.06
    POSITIVE LOGITS
    (sync
    0.07
    áct
    0.06
    18
    0.06
    结束
    0.06
     TEX
    0.06
     alleen
    0.06
     digest
    0.06
     водой
    0.06
    γγ
    0.06
    เกอร
    0.06
    Act Density 0.002%

    No Known Activations