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

    Neuronpedia

    INDEX
    Explanations

    repeated syllables or phonetic patterns in names and words

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

    female names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ManagedBean
    -0.47
    flink
    -0.44
     שוליים
    -0.41
     z
    -0.39
    tagHelper
    -0.39
     Nazareth
    -0.37
    KURZBESCHREIBUNG
    -0.37
     Roskov
    -0.37
    leth
    -0.36
    OUNTS
    -0.36
    POSITIVE LOGITS
    expandindo
    0.56
    Vicki
    0.55
     Terri
    0.53
    Terri
    0.52
    enderror
    0.51
    Jeanne
    0.50
    Gail
    0.50
     Vicki
    0.50
    Carol
    0.49
    Laurie
    0.48
    Act Density 0.079%

    No Known Activations