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

    Neuronpedia

    INDEX
    Explanations

    writing to express interest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ListOf
    0.36
     સામ
    0.36
    これからも
    0.35
    ക്രമ
    0.35
    XmlElement
    0.35
    പ്പി
    0.35
     받을
    0.35
     самим
    0.35
     levied
    0.35
    Prol
    0.35
    POSITIVE LOGITS
     intérêt
    0.49
     interés
    0.43
    闗
    0.40
     signaling
    0.39
     interesse
    0.39
     enquire
    0.37
    綺
    0.37
     enquiry
    0.37
    饑
    0.37
    pulsewidth
    0.37
    Act Density 0.002%

    No Known Activations