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

    Neuronpedia

    INDEX
    Explanations

    Math calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     意
    -0.06
    contacts
    -0.06
     PASS
    -0.06
    وز
    -0.06
     např
    -0.06
     foss
    -0.05
     jer
    -0.05
    озі
    -0.05
    シュ
    -0.05
    :w
    -0.05
    POSITIVE LOGITS
    .seconds
    0.07
     []↵↵
    0.07
    жень
    0.07
    ph
    0.07
     Byrne
    0.07
     Больш
    0.07
    .Hash
    0.07
     Pradesh
    0.06
    	tv
    0.06
    룹
    0.06
    Act Density 0.012%

    No Known Activations