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

    Neuronpedia

    INDEX
    Explanations

    `converts` `BINARY` `distant` `two`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     १००
    0.43
     स्वाद
    0.39
    ቾ
    0.38
    ۸
    0.37
    Ttest
    0.36
    ১০
    0.36
    で使用
    0.36
     jod
    0.36
    ɰ
    0.36
    effici
    0.35
    POSITIVE LOGITS
     two
    0.48
     Two
    0.44
    Two
    0.40
    two
    0.37
     role
    0.36
    Policy
    0.34
     TWO
    0.33
    role
    0.33
    Shop
    0.33
     dua
    0.33
    Act Density 0.004%

    No Known Activations