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

    Neuronpedia

    INDEX
    Explanations

    concepts related to self-reference and individuality

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

    self- prefix abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.83
     Infórmanos
    -0.81
     Audiodateien
    -0.75
     parachoque
    -0.75
     suaminya
    -0.74
    antMatchers
    -0.74
    Tikang
    -0.73
     kasarigan
    -0.72
    tvguidetime
    -0.72
    IndentedString
    -0.69
    POSITIVE LOGITS
    Self
    0.52
     Self
    0.47
     self
    0.42
     scientific
    0.40
     SELF
    0.39
     Rtl
    0.37
    Auto
    0.37
     Scientific
    0.37
     科学
    0.37
     Auto
    0.36
    Act Density 0.009%

    No Known Activations