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

    Neuronpedia

    INDEX
    Explanations

    instances of possessive or contracted forms in the text

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

    reflexive verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.89
    VersionUID
    -0.82
    parsedMessage
    -0.72
     AssemblyCompany
    -0.71
    colhead
    -0.63
     noDo
    -0.61
    出版年
    -0.60
    ="@+
    -0.60
     صوتيه
    -0.60
    ValueStyle
    -0.59
    POSITIVE LOGITS
     sich
    0.76
     zich
    0.66
    sich
    0.53
     se
    0.49
     się
    0.47
     self
    0.45
    相
    0.43
     hacerse
    0.42
     Sich
    0.41
     goes
    0.40
    Act Density 0.011%

    No Known Activations