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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	QString
    -0.07
    Kenn
    -0.07
    _ROUT
    -0.06
     Machines
    -0.06
    -med
    -0.06
    poke
    -0.06
     reimburse
    -0.06
    welcome
    -0.06
     благ
    -0.06
     enquiry
    -0.06
    POSITIVE LOGITS
     deselect
    0.07
    onder
    0.07
     rk
    0.06
    hip
    0.06
     sch
    0.06
    .Material
    0.06
    rk
    0.06
    deck
    0.06
    (fill
    0.06
     Netflix
    0.06
    Act Density 0.044%

    No Known Activations