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

    Neuronpedia

    INDEX
    Explanations

    these

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inv
    -0.07
     boil
    -0.07
    remark
    -0.07
    ян
    -0.07
    _TYPEDEF
    -0.06
    neum
    -0.06
    inc
    -0.06
    Pred
    -0.06
     Surveillance
    -0.06
    ais
    -0.06
    POSITIVE LOGITS
    ],↵
    0.06
    (de
    0.06
     ];↵↵
    0.06
    .)↵↵
    0.06
    >').
    0.06
     текст
    0.06
    )),↵
    0.06
     söylem
    0.06
    =sub
    0.06
     betr
    0.06
    Act Density 0.243%

    No Known Activations