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

    Neuronpedia

    INDEX
    Explanations

    words related to political actions and social justice issues

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

    actions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     său
    -0.46
     dumne
    -0.44
     régime
    -0.43
     dieťa
    -0.43
     singur
    -0.42
     Anpass
    -0.42
     dítě
    -0.41
     séjours
    -0.41
     intérêts
    -0.41
     presidencial
    -0.41
    POSITIVE LOGITS
    NameInMap
    0.56
     themselves
    0.55
     själva
    0.53
     utafitiHapana
    0.53
     Administrativna
    0.50
     Their
    0.46
    themselves
    0.45
     getUsers
    0.44
     assholes
    0.43
    ″]
    0.42
    Act Density 0.393%

    No Known Activations