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

    Neuronpedia

    INDEX
    Explanations

    proper names, particularly of individuals

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

    names followed by numbers or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erov
    -0.43
     épaules
    -0.43
    DIPSETTING
    -0.42
    recated
    -0.41
     itself
    -0.40
    prevState
    -0.40
    dataTables
    -0.40
    edor
    -0.39
     himself
    -0.39
    builder
    -0.38
    POSITIVE LOGITS
    rillation
    0.39
    NUMX
    0.39
    
    0.36
     onResponse
    0.35
     allemaal
    0.35
     strs
    0.34
     defaultstate
    0.34
    RTEX
    0.34
     setDescription
    0.33
    ensement
    0.33
    Act Density 0.171%

    No Known Activations