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

    Neuronpedia

    INDEX
    Explanations

    references to specific positions or locations within a structure or system

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

    midway

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.65
     itſelf
    -0.57
     tranſ
    -0.56
     ſche
    -0.55
     faſt
    -0.54
     chofe
    -0.54
     fubject
    -0.53
     raiſ
    -0.52
    ſelves
    -0.51
     themſelves
    -0.51
    POSITIVE LOGITS
    mid
    2.03
     mid
    1.82
    Mid
    1.60
    MID
    1.55
     MID
    1.50
     Mid
    1.47
    mids
    1.12
     mids
    1.08
     midterm
    1.05
     midpoint
    1.02
    Act Density 0.008%

    No Known Activations