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

    Neuronpedia

    INDEX
    Explanations

    some form of decision-making or transitions in life events

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

    choices and alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Colorado
    -0.37
    %)$
    -0.36
    stag
    -0.36
     DIN
    -0.35
    MACH
    -0.34
     Cm
    -0.34
     Mg
    -0.34
    ⇑
    -0.34
    المناصب
    -0.34
     cm
    -0.34
    POSITIVE LOGITS
     instead
    0.57
     AssemblyCulture
    0.57
    instead
    0.57
    IntoConstraints
    0.56
     finalement
    0.56
    Espèce
    0.50
    Instead
    0.49
     letzt
    0.49
     zamiast
    0.49
    SuppressLint
    0.48
    Act Density 0.063%

    No Known Activations