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

    Neuronpedia

    INDEX
    Explanations

    code and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -bedroom
    -0.08
    uite
    -0.07
     vbox
    -0.07
     ′
    -0.06
     Onc
    -0.06
     rhyth
    -0.06
     RJ
    -0.06
     Creek
    -0.06
    -fe
    -0.06
     programas
    -0.06
    POSITIVE LOGITS
     '".$_
    0.07
    +b
    0.07
     cheg
    0.06
     pokud
    0.06
    =value
    0.06
     knull
    0.06
     deceive
    0.06
    ','=','
    0.06
    )findViewById
    0.06
     �
    0.06
    Act Density 0.030%

    No Known Activations