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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ities
    -0.07
    ...",↵
    -0.07
    력
    -0.07
    %%
    -0.06
     Наз
    -0.06
     %%
    -0.06
     voucher
    -0.06
    	or
    -0.06
    .obs
    -0.06
     міжнарод
    -0.06
    POSITIVE LOGITS
    revision
    0.07
     Lightweight
    0.06
     réuss
    0.06
    folio
    0.06
     adaptable
    0.06
     IllegalAccessException
    0.06
    internet
    0.06
     을
    0.06
     conservation
    0.06
     displayName
    0.06
    Act Density 0.015%

    No Known Activations