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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ఆమె
    -0.07
     tow
    -0.07
    -0.07
    ిశ
    -0.07
     corret
    -0.07
    ਾਪ
    -0.07
    (rc
    -0.07
     recall
    -0.07
    _TEMP
    -0.07
     rc
    -0.07
    POSITIVE LOGITS
     overridden
    0.12
    abstract
    0.12
    .abstract
    0.12
     Abstract
    0.11
     специф
    0.11
     subclasses
    0.11
     abstract
    0.10
    	override
    0.10
     ABSTRACT
    0.10
     override
    0.09
    Act Density 0.005%
    No Known Activations