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

    Neuronpedia

    INDEX
    Explanations

    seem to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vermutlich
    0.28
    𝒂
    0.27
    邮
    0.27
    º
    0.26
     сообщение
    0.26
    ন
    0.26
    эд
    0.25
    uting
    0.25
     заявление
    0.25
     তাহাদিগের
    0.25
    POSITIVE LOGITS
     destined
    0.37
     inexplic
    0.36
     awfully
    0.36
     overly
    0.36
     poised
    0.34
     seem
    0.34
     unduly
    0.33
    像是
    0.32
     disproportion
    0.32
     insurmountable
    0.32
    Act Density 0.018%

    No Known Activations