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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fre
    -0.06
     Schro
    -0.06
     prior
    -0.06
    해야
    -0.06
     affinity
    -0.06
    (Entity
    -0.05
     deton
    -0.05
     Hud
    -0.05
     achie
    -0.05
    º
    -0.05
    POSITIVE LOGITS
    ishes
    0.07
    练
    0.07
    avings
    0.07
    ΜΑ
    0.07
    ована
    0.07
     Environment
    0.07
    	JOptionPane
    0.07
    vál
    0.07
     マ
    0.07
     змін
    0.07
    Act Density 0.023%

    No Known Activations