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

    Neuronpedia

    INDEX
    Explanations

    expressing personal thoughts and beliefs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
                     
    0.30
    ः
    0.30
     voici
    0.30
               
    0.28
     WebSocket
    0.27
     framebuffer
    0.27
    瀣
    0.27
     insolvent
    0.27
             
    0.26
    ድረ
    0.26
    POSITIVE LOGITS
    ho
    0.33
    ki
    0.32
    ch
    0.29
    so
    0.29
    cha
    0.29
    je
    0.27
    ks
    0.27
    that
    0.27
    kie
    0.27
    kij
    0.26
    Act Density 0.042%

    No Known Activations