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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possibilities and potential outcomes

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

    positive attributes and new states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TypedDataSet
    -0.65
     AssemblyVersion
    -0.59
     Италијани
    -0.59
    хьтан
    -0.58
     kohdetta
    -0.58
     Biôgrafia
    -0.57
    ArrowToggle
    -0.56
     Савезне
    -0.55
    ніципа
    -0.55
    Derbyniad
    -0.54
    POSITIVE LOGITS
     препратки
    0.44
    TemporalType
    0.40
     مشين
    0.39
     sonda
    0.37
    Gizmos
    0.36
    +#+#
    0.36
     Probe
    0.36
     Proof
    0.36
     semblables
    0.35
     financières
    0.35
    Act Density 0.011%

    No Known Activations