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

    Neuronpedia

    INDEX
    Explanations

    quantifier or modal verbs indicating possibility or likelihood

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

    possibility or speculation with have/be/not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ICF
    -0.49
    כי
    -0.48
    şti
    -0.46
    raszamy
    -0.44
    IUM
    -0.44
    UUM
    -0.44
     lze
    -0.44
    idable
    -0.43
    ็น
    -0.43
    utiny
    -0.43
    POSITIVE LOGITS
     MAY
    0.45
    ArgsConstructor
    0.45
     may
    0.44
    XmlRootElement
    0.43
     May
    0.43
    middels
    0.41
    ]**
    0.40
    ReusableCell
    0.39
    __((
    0.39
     MutableLiveData
    0.38
    Act Density 0.036%

    No Known Activations