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

    Neuronpedia

    INDEX
    Explanations

    P words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    观测
    0.48
    algorith
    0.48
     stvari
    0.47
    ק
    0.47
     miesią
    0.46
    יל
    0.45
    贫
    0.45
     potere
    0.45
     instancias
    0.45
     steigt
    0.44
    POSITIVE LOGITS
     P
    0.54
    PPI
    0.53
    P
    0.52
     PA
    0.50
    PE
    0.50
    PN
    0.47
     PN
    0.46
    </code>
    0.46
     PCC
    0.46
     p
    0.46
    Act Density 0.253%

    No Known Activations