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

    Neuronpedia

    INDEX
    Explanations

    gran

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    両
    -0.07
    ีท
    -0.07
     adapted
    -0.06
     Hive
    -0.06
     تش
    -0.06
     เน
    -0.06
     surgeon
    -0.06
    _tE
    -0.06
     Toro
    -0.06
     mixed
    -0.06
    POSITIVE LOGITS
     isChecked
    0.07
    บบ
    0.07
    armac
    0.07
     messenger
    0.07
    UTTON
    0.07
    oplast
    0.06
    _exception
    0.06
     narration
    0.06
     properly
    0.06
     decoder
    0.06
    Act Density 0.000%

    No Known Activations