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

    Neuronpedia

    INDEX
    Explanations

    they present

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    compliant
    0.40
     compliant
    0.40
     dava
    0.39
     പാല
    0.38
     justifications
    0.38
     باك
    0.37
    消化
    0.36
     consideración
    0.36
    нцип
    0.36
     महंगे
    0.35
    POSITIVE LOGITS
    这些人
    0.40
    kun
    0.40
     डिस्टेंस
    0.37
    efa
    0.37
     lightest
    0.37
     மஞ்சள்
    0.37
    tki
    0.37
     সক
    0.36
     കൊ
    0.36
     Coch
    0.36
    Act Density 0.000%

    No Known Activations