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

    Neuronpedia

    INDEX
    Explanations

    specific adjectives and their variations used to describe things in a context

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

    conditional states or presence/absence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mijne
    -0.58
    hdashline
    -0.50
    cVar
    -0.48
     joten
    -0.48
     zijne
    -0.48
     nicio
    -0.46
     zoude
    -0.45
    theless
    -0.44
    tshell
    -0.44
     hinweg
    -0.44
    POSITIVE LOGITS
     puro
    0.63
    Ultimo
    0.62
    ativo
    0.59
     Americano
    0.59
     americano
    0.58
    UnknownFieldSet
    0.56
     largo
    0.56
     Fino
    0.56
    sivo
    0.55
    politico
    0.55
    Act Density 0.007%

    No Known Activations