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

    Neuronpedia

    INDEX
    Explanations

    4 or 2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    าง
    -0.06
    _opacity
    -0.06
    르
    -0.06
     Ved
    -0.06
    Leaders
    -0.06
    'O
    -0.06
    Interpreter
    -0.06
    	font
    -0.06
    فع
    -0.06
    mailbox
    -0.06
    POSITIVE LOGITS
     transmitter
    0.07
    国内
    0.07
     selfish
    0.06
     κο
    0.06
     veriyor
    0.06
     rtl
    0.06
     dieser
    0.06
     дов
    0.06
    victim
    0.06
    -expression
    0.06
    Act Density 0.001%

    No Known Activations