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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal feelings and relationships

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

    things that could do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \{\\
    -0.54
    LookAnd
    -0.52
    iecie
    -0.48
    Personendaten
    -0.45
     téléphonique
    -0.45
    ViewFeatures
    -0.44
     joão
    -0.44
    ViewImports
    -0.43
    AntiForgeryToken
    -0.40
     intptr
    -0.40
    POSITIVE LOGITS
    Datuak
    0.50
    SpringRunner
    0.47
    morrow
    0.42
     gespannt
    0.42
    Pró
    0.40
    BERG
    0.40
     resolution
    0.39
    reel
    0.38
    smöglichkeiten
    0.38
    WithMany
    0.38
    Act Density 0.040%

    No Known Activations