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

    Neuronpedia

    INDEX
    Explanations

    receiving advice and support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ์
    0.67
    Messenger
    0.67
    и
    0.67
    عت
    0.65
     Respublik
    0.65
     పాటు
    0.64
    டித்து
    0.64
    obuf
    0.64
    ய்
    0.63
    Fog
    0.62
    POSITIVE LOGITS
    받
    1.31
     from
    1.24
     received
    1.24
    ຈາກ
    1.14
     Received
    1.09
     från
    1.08
    来自
    1.07
    を受ける
    1.07
    จาก
    1.05
    Received
    1.02
    Act Density 0.373%

    No Known Activations