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

    Neuronpedia

    INDEX
    Explanations

    domain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     조선
    -0.07
    $headers
    -0.07
     жен
    -0.06
     Ảnh
    -0.06
    logout
    -0.06
     일부
    -0.06
    フォ
    -0.06
     조금
    -0.06
     buổi
    -0.06
     []).
    -0.06
    POSITIVE LOGITS
    ุบาล
    0.06
     perm
    0.06
    _resource
    0.06
    _GENERAL
    0.06
     worthwhile
    0.06
     differ
    0.06
    integral
    0.06
     ranging
    0.06
     domains
    0.06
     considerable
    0.06
    Act Density 0.007%

    No Known Activations