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

    Neuronpedia

    INDEX
    Explanations

    achievable in SMART goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ширина
    0.40
     ፋ
    0.39
    শ্
    0.37
     coordin
    0.36
    ޒ
    0.36
     dwRes
    0.36
    Gamma
    0.35
    のだが
    0.35
    慶
    0.35
     పరిశ
    0.34
    POSITIVE LOGITS
     relevant
    0.36
     לצ
    0.34
    relevant
    0.34
    ved
    0.33
     Му
    0.33
     Ведь
    0.33
    blatt
    0.33
    fid
    0.32
    state
    0.32
    tere
    0.32
    Act Density 0.002%

    No Known Activations