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

    Neuronpedia

    INDEX
    Explanations

    Options, particularly former/latter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ‍
    0.45
    ossi
    0.40
    
    0.40
    AN
    0.39
    ”;
    0.39
    reter
    0.39
    ළ
    0.38
    ­
    0.37
    ct
    0.37
    my
    0.36
    POSITIVE LOGITS
     latter
    0.79
    后者
    0.75
    前者
    0.63
     vooral
    0.57
     particularly
    0.57
     někter
    0.56
     especially
    0.55
     особенно
    0.55
     niektor
    0.55
     cualquiera
    0.52
    Act Density 0.258%

    No Known Activations