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

    Neuronpedia

    INDEX
    Explanations

    words that convey strong opinions or significant impacts

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

    degree or magnitude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الحياه
    -0.60
    ⟬
    -0.58
    ScopeManager
    -0.55
    SequentialGroup
    -0.55
     transfieras
    -0.54
    MemoryWarning
    -0.54
     kaarangay
    -0.54
    :✨
    -0.54
    Portail
    -0.53
    rungsseite
    -0.53
    POSITIVE LOGITS
    ,
    0.47
     enough
    0.45
     and
    0.44
     but
    0.40
     wide
    0.38
    ;
    0.38
     crí
    0.38
    :
    0.38
     far
    0.38
     only
    0.37
    Act Density 0.045%

    No Known Activations