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

    Neuronpedia

    INDEX
    Explanations

    the concept of uniqueness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    unique aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.52
    IntoConstraints
    -0.50
     endfor
    -0.48
    weiterlesen
    -0.47
     BoxDecoration
    -0.47
     հղումներ
    -0.46
    dbach
    -0.45
     AppBar
    -0.44
     poveznice
    -0.44
     Bacteriol
    -0.43
    POSITIVE LOGITS
     unique
    2.02
    unique
    1.79
    Unique
    1.71
     Unique
    1.71
     UNIQUE
    1.66
     uniquely
    1.56
    UNIQUE
    1.53
     uniqueness
    1.45
     uniques
    1.44
     уника
    1.38
    Act Density 0.009%

    No Known Activations