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

    Neuronpedia

    INDEX
    Explanations

    phrases related to etiquette and social behavior

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

    Text following ordinal numbers or punctuation

    np_acts-logits-general · gemini-2.0-flash

    Power steering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.61
    ſicht
    -0.59
    msgTypes
    -0.59
    expandindo
    -0.58
    힣
    -0.57
     nakalista
    -0.56
     IFTT
    -0.55
    قایناق‌لار
    -0.54
    NameInMap
    -0.53
     티즈
    -0.52
    POSITIVE LOGITS
    The
    0.60
     The
    0.52
    Although
    0.52
    While
    0.50
    Unlike
    0.47
     Although
    0.47
    If
    0.47
    Though
    0.46
    Since
    0.46
    In
    0.46
    Act Density 0.055%

    No Known Activations