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

    Neuronpedia

    INDEX
    Explanations

    terms related to heightened states, particularly those describing intensity or advanced qualities

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

    hyper-intensifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     server
    -0.42
     Inspir
    -0.40
     Guid
    -0.39
     Linen
    -0.38
     recipro
    -0.38
    Conver
    -0.37
    VEND
    -0.37
    育
    -0.37
     Login
    -0.36
     settlement
    -0.36
    POSITIVE LOGITS
     ultra
    0.66
     <<<<<<<<<<<<<<
    0.62
     extremadamente
    0.61
    Extremely
    0.56
     highly
    0.54
    SizeF
    0.54
     extremely
    0.53
     Extremely
    0.52
     hyper
    0.51
     שוליים
    0.51
    Act Density 0.010%

    No Known Activations