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

    Neuronpedia

    INDEX
    Explanations

    sentence end

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ަލ
    0.64
    ɒ
    0.64
    ioutil
    0.63
    draggable
    0.63
    blogger
    0.61
     хвата
    0.60
    adl
    0.60
     unital
    0.59
    DIA
    0.56
     Blogs
    0.55
    POSITIVE LOGITS
     undergo
    0.71
     undergoing
    0.68
     treatment
    0.67
     glowing
    0.66
     financing
    0.64
     established
    0.64
     largest
    0.63
     undergone
    0.61
     accomplish
    0.60
     begun
    0.59
    Act Density 0.000%

    No Known Activations