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

    Neuronpedia

    INDEX
    Explanations

    generally like things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tubig
    0.55
     najważ
    0.55
    formation
    0.54
     wygod
    0.53
     cerveau
    0.52
     datth
    0.51
     họa
    0.49
    ردن
    0.49
     vị
    0.48
     phénomènes
    0.48
    POSITIVE LOGITS
    sp
    0.50
     Joy
    0.46
     Cust
    0.44
     Arena
    0.42
     Friend
    0.41
    也是
    0.41
     peers
    0.41
    зви
    0.41
     Sh
    0.40
     Gold
    0.40
    Act Density 0.004%

    No Known Activations