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

    Neuronpedia

    INDEX
    Explanations

    encompassing assessment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     labour
    0.42
    労働
    0.38
    Came
    0.38
    CUSSION
    0.38
    City
    0.37
    COT
    0.36
    そこで
    0.36
     explicação
    0.36
    经
    0.35
     BTS
    0.35
    POSITIVE LOGITS
    affer
    0.40
     ins
    0.39
    riff
    0.39
    izma
    0.39
     airfoil
    0.38
    itled
    0.38
     veins
    0.38
    quellen
    0.38
    izing
    0.37
     చేసుకోవ
    0.37
    Act Density 0.000%

    No Known Activations