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

    Neuronpedia

    INDEX
    Explanations

    contribute to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FBSDKSettings
    0.37
     Weston
    0.35
    apping
    0.35
    łach
    0.34
    arei
    0.33
    ऱ्यावर
    0.32
    arians
    0.32
     äl
    0.32
    agir
    0.32
    avak
    0.32
    POSITIVE LOGITS
     contribute
    0.97
     Contribute
    0.78
     contributing
    0.77
     contribu
    0.77
     contrib
    0.76
     contributes
    0.76
     contribut
    0.74
     contribuir
    0.74
     contributed
    0.74
     contribuer
    0.71
    Act Density 0.005%

    No Known Activations