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

    Neuronpedia

    INDEX
    Explanations

    inspect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    scatter
    -0.07
    _ACC
    -0.07
     dynamically
    -0.07
    abe
    -0.07
    -0.07
    ちは
    -0.07
    project
    -0.07
    ,@
    -0.07
     shuffle
    -0.07
    ิด
    -0.07
    POSITIVE LOGITS
     disclosures
    0.11
     inspections
    0.10
     disclosure
    0.10
     compradores
    0.10
     disclose
    0.09
    Informe
    0.09
     reconnaissance
    0.09
     వెల్లడ
    0.09
     forensic
    0.09
     homeowners
    0.09
    Act Density 0.009%
    No Known Activations