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

    Neuronpedia

    INDEX
    Explanations

    swimming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bezirk
    0.44
     december
    0.41
     മേഖ
    0.41
     :,
    0.41
     kecamatan
    0.41
    gyi
    0.40
    otri
    0.40
    ve
    0.40
     futuras
    0.40
     الاح
    0.39
    POSITIVE LOGITS
    ುತ್ತಿದ್ದ
    0.38
    శ్వ
    0.37
     swimming
    0.37
    '];
    0.36
     للج
    0.36
    Morse
    0.36
     Anatomy
    0.35
    Swimming
    0.35
     Sweater
    0.35
    游泳
    0.35
    Act Density 0.004%

    No Known Activations