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

    Neuronpedia

    INDEX
    Explanations

    Code and directory structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Territory
    -0.07
    _h
    -0.06
     PREFIX
    -0.06
     Keystone
    -0.06
    antity
    -0.06
     Destiny
    -0.06
     condiciones
    -0.06
    inecraft
    -0.06
     territory
    -0.06
    重点
    -0.06
    POSITIVE LOGITS
     hotline
    0.07
    -auth
    0.07
     первый
    0.06
     []),↵
    0.06
    /filepath
    0.06
     ภาษ
    0.06
    count
    0.06
     refers
    0.06
     तम
    0.06
    ğü
    0.06
    Act Density 0.103%

    No Known Activations