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

    Neuronpedia

    INDEX
    Explanations

    k

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ตก
    -0.09
     socially
    -0.08
    Agree
    -0.08
    出售
    -0.08
     সরকারের
    -0.08
    Department
    -0.08
     ઉત
    -0.08
     succession
    -0.08
    ास्थ
    -0.08
    pliance
    -0.08
    POSITIVE LOGITS
     capabilities
    0.12
     memory
    0.11
     Memory
    0.11
    容量
    0.11
     capability
    0.11
    .memory
    0.10
     capacités
    0.10
     geheugen
    0.10
     GPT
    0.10
     capacité
    0.10
    Act Density 0.007%

    No Known Activations