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

    Neuronpedia

    INDEX
    Explanations

    code/data structures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DMI
    -0.07
    ormap
    -0.07
    ngle
    -0.07
    criptive
    -0.06
    IEL
    -0.06
     warned
    -0.06
    _counters
    -0.06
    -0.06
    incer
    -0.06
     unilateral
    -0.06
    POSITIVE LOGITS
     Scheduled
    0.07
     xf
    0.06
     replica
    0.06
    .equalsIgnoreCase
    0.06
     assoc
    0.06
    .bus
    0.06
    카지노
    0.06
     Cas
    0.06
     �
    0.06
    	match
    0.06
    Act Density 0.024%

    No Known Activations