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

    Neuronpedia

    INDEX
    Explanations

    от

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    achi
    -0.07
    ेह
    -0.07
    _PROXY
    -0.06
    \"></
    -0.06
     shipped
    -0.06
     Kaplan
    -0.06
    /google
    -0.06
    IGO
    -0.06
     panda
    -0.06
     Cypress
    -0.06
    POSITIVE LOGITS
     DT
    0.07
     horas
    0.07
    phan
    0.06
     줄
    0.06
     由
    0.06
    ่งชาต
    0.06
    속
    0.06
     �
    0.06
    �
    0.06
     돈
    0.06
    Act Density 0.003%

    No Known Activations