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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating spatial or contextual relationships

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

    Prepositions

    np_acts-logits-general · gemini-2.0-flash

    prepositions followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WithIOException
    -0.70
     chi̍t
    -0.69
     referrerpolicy
    -0.69
     AssemblyTitle
    -0.67
    __':
    -0.66
     ModelRenderer
    -0.66
    IsPostBack
    -0.66
    uxxxx
    -0.66
    Enders
    -0.64
    ValueGenerated
    -0.64
    POSITIVE LOGITS
    たまた
    0.62
    Через
    0.60
    Σε
    0.57
     importantly
    0.55
     וב
    0.53
     ho
    0.49
    లాలు
    0.49
     In
    0.48
    liny
    0.48
    bigcup
    0.48
    Act Density 0.350%

    No Known Activations