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

    Neuronpedia

    INDEX
    Explanations

    assessing trust and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BleStatus
    0.59
    ﺕ
    0.58
     básico
    0.57
     chemokine
    0.57
     Bugünkü
    0.56
     grafo
    0.54
    TaskPojo
    0.54
    τισ
    0.54
    ໃຊ
    0.54
    ್ಟ
    0.53
    POSITIVE LOGITS
    ↵
    0.77
    ,
    0.67
     never
    0.67
    el
    0.66
    h
    0.65
     don
    0.64
     wouldn
    0.64
    ’,
    0.63
        
    0.63
    se
    0.60
    Act Density 0.065%

    No Known Activations