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

    Neuronpedia

    INDEX
    Explanations

    backslash characters used in programming or formatting contexts

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

    LaTeX end tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Input
    -0.49
     shore
    -0.47
    隅
    -0.46
    raded
    -0.46
     Meier
    -0.44
     Suzuki
    -0.44
    fice
    -0.44
    SetItem
    -0.44
    vfs
    -0.44
    malink
    -0.44
    POSITIVE LOGITS
     feroit
    0.55
     <<<<<<<<<<<<<<
    0.52
    yntaxException
    0.51
    Personensuche
    0.49
     auroit
    0.49
     voordelen
    0.46
     chrétien
    0.44
     religione
    0.44
     étoit
    0.44
     enfans
    0.43
    Act Density 0.002%

    No Known Activations