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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "for" and related phrasing

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

    as for a topic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.57
    rrggbb
    -0.56
    DebuggerStep
    -0.56
     vectorielles
    -0.53
     dormitórios
    -0.51
     réguli
    -0.50
     appartamento
    -0.48
     extérieures
    -0.48
     américains
    -0.47
    󠁿
    -0.47
    POSITIVE LOGITS
    至于
    0.71
    أما
    0.63
    至於
    0.62
     أما
    0.58
    Adapun
    0.50
    Còn
    0.42
     kasarigan
    0.40
    Sedangkan
    0.40
    ngdoc
    0.40
     mengenai
    0.37
    Act Density 0.037%

    No Known Activations