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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DOJ
    -0.06
    ��
    -0.06
     Albums
    -0.06
     заступ
    -0.06
    úb
    -0.06
     exile
    -0.06
    WITHOUT
    -0.06
    ідом
    -0.06
    .psi
    -0.06
     meaning
    -0.06
    POSITIVE LOGITS
     consc
    0.08
    $l
    0.07
     davranış
    0.07
     七
    0.06
     ویژگی
    0.06
     swaps
    0.06
    .↵↵↵↵↵↵↵↵↵↵
    0.06
     getAddress
    0.06
    bows
    0.06
     Datensch
    0.06
    Act Density 0.000%

    No Known Activations