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

    Neuronpedia

    INDEX
    Explanations

    knowledge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unnatural
    -0.07
    �ng
    -0.07
    perfect
    -0.06
    .bits
    -0.06
    addafi
    -0.06
    कर
    -0.06
     unjust
    -0.06
     ніколи
    -0.06
    ArgsConstructor
    -0.06
     lump
    -0.06
    POSITIVE LOGITS
    ]↵↵↵↵
    0.06
     manifestations
    0.06
     SAVE
    0.06
     presets
    0.06
    %"><
    0.06
    貸
    0.06
     fmt
    0.06
    ITLE
    0.06
     тен
    0.06
    ’en
    0.06
    Act Density 0.010%

    No Known Activations