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

    Neuronpedia

    INDEX
    Explanations

    ple

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drinks
    -0.08
    	dst
    -0.07
    	part
    -0.07
     You
    -0.07
    形成
    -0.07
     tapped
    -0.06
     CO
    -0.06
     đón
    -0.06
     notifier
    -0.06
     isa
    -0.06
    POSITIVE LOGITS
     Cle
    0.08
    arith
    0.06
    DataExchange
    0.06
    CLE
    0.06
    егда
    0.06
     Glen
    0.06
    terdam
    0.06
    PLE
    0.06
    ©
    0.06
     Cleans
    0.06
    Act Density 0.064%

    No Known Activations