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

    Neuronpedia

    INDEX
    Explanations

    General conversation/discussion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UIViewController
    -0.07
     ecology
    -0.07
    442
    -0.07
    ogenic
    -0.06
    	ID
    -0.06
     revolutions
    -0.06
    _model
    -0.06
     mapa
    -0.06
     FileOutputStream
    -0.06
     STATE
    -0.06
    POSITIVE LOGITS
     putting
    0.07
    ілля
    0.06
     TokenType
    0.06
    거나
    0.06
     detached
    0.06
     hepsi
    0.06
    omain
    0.06
     adding
    0.06
     uniquely
    0.06
    ured
    0.06
    Act Density 0.028%

    No Known Activations