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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pictures
    -0.06
     weg
    -0.06
     Distance
    -0.06
     koneč
    -0.06
     нуж
    -0.06
     줄
    -0.06
     direct
    -0.06
     athletics
    -0.06
    -menu
    -0.05
    	post
    -0.05
    POSITIVE LOGITS
     он
    0.07
    ayız
    0.06
    (error
    0.06
     पहल
    0.06
    .slider
    0.06
     Spoon
    0.06
    样子
    0.06
     invoices
    0.06
    .state
    0.06
    .enemy
    0.06
    Act Density 0.043%

    No Known Activations