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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DEC
    -0.08
    avam
    -0.08
    �
    -0.08
    wear
    -0.07
     thrives
    -0.07
     cần
    -0.07
    erns
    -0.07
     கோ
    -0.07
    Nano
    -0.07
    constitution
    -0.07
    POSITIVE LOGITS
     смыс
    0.08
     স্থানীয়
    0.08
     calor
    0.07
     Heimat
    0.07
     Jadi
    0.07
     Commissioners
    0.07
    Она
    0.07
     Commissie
    0.07
     depr
    0.07
     এলাকার
    0.07
    Act Density 0.010%

    No Known Activations