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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate consistency or universality

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

    all times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    withIdentifier
    -0.40
     clutch
    -0.37
    SequentialGroup
    -0.36
     celeb
    -0.36
    ChildScrollView
    -0.35
    JspWriter
    -0.35
     atr
    -0.35
    rungsseite
    -0.34
    mappedBy
    -0.34
    ATR
    -0.34
    POSITIVE LOGITS
    IVEREF
    0.52
    まま
    0.51
     throughout
    0.49
    Microkernel
    0.49
     Taktlose
    0.49
     FOREVER
    0.49
    IntoConstraints
    0.48
    ALWAYS
    0.48
     mãi
    0.47
    forever
    0.47
    Act Density 0.199%

    No Known Activations