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

    Neuronpedia

    INDEX
    Explanations

    user-friendly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    పథ
    0.40
    ponses
    0.38
     भागीदारों
    0.37
     партне
    0.37
    addena
    0.36
     polarized
    0.36
     неве
    0.36
    eterminate
    0.36
    éroport
    0.35
    斂
    0.35
    POSITIVE LOGITS
     friendly
    3.31
     Friendly
    3.22
    Friendly
    3.19
    friendly
    3.08
     friendliness
    2.63
     freund
    2.59
    友好
    2.53
     друже
    2.53
     FRIEND
    2.52
    友
    2.36
    Act Density 0.036%

    No Known Activations