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

    Neuronpedia

    INDEX
    Explanations

    What

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    包括
    -0.06
    按照
    -0.06
     rov
    -0.06
     btnSave
    -0.06
     frü
    -0.06
    DetailsService
    -0.06
     malicious
    -0.06
     Çin
    -0.06
    ราะ
    -0.06
    ผ
    -0.06
    POSITIVE LOGITS
    essoa
    0.07
    ятно
    0.07
    ricula
    0.06
     lessons
    0.06
     She
    0.06
    jom
    0.06
     adapted
    0.06
     Strategies
    0.06
     Ка
    0.06
     addition
    0.06
    Act Density 0.038%

    No Known Activations