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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to individual responsibility or key roles within a group context

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

    one(s) who

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abaikan
    -0.34
    ställ
    -0.32
    stüt
    -0.32
    ╹
    -0.31
    滤
    -0.31
     asesino
    -0.30
     superfí
    -0.30
    萩
    -0.30
    弱い
    -0.30
     muchos
    -0.30
    POSITIVE LOGITS
    AddTagHelper
    0.68
    IntoConstraints
    0.64
    awaiter
    0.57
     OnTrigger
    0.57
    CppMethod
    0.55
     Anſ
    0.54
     FixedUpdate
    0.53
    instancetype
    0.53
    ScopeManager
    0.52
    ſelf
    0.52
    Act Density 0.016%

    No Known Activations