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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ובר
    -0.07
     ledger
    -0.07
     nig
    -0.07
    أوراق
    -0.06
    �
    -0.06
     Idle
    -0.06
    leader
    -0.06
     список
    -0.06
    .Port
    -0.06
    周刊
    -0.06
    POSITIVE LOGITS
     fieldType
    0.07
     bi
    0.07
     í
    0.07
     careful
    0.07
     qualifying
    0.07
     fieldName
    0.06
     resid
    0.06
    }','
    0.06
     concussion
    0.06
     tsl
    0.06
    Act Density 0.030%

    No Known Activations