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

    Neuronpedia

    INDEX
    Explanations

    whole

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    velopp
    0.50
     καὶ
    0.50
    芑
    0.50
    qvarna
    0.50
    Samp
    0.49
     സാധ്യത
    0.48
    faire
    0.47
    Surviv
    0.47
    可以说
    0.47
    es
    0.46
    POSITIVE LOGITS
     maravilh
    0.47
     unserer
    0.47
     slaughter
    0.44
     osmotic
    0.44
     isolating
    0.44
     investigating
    0.43
     hammering
    0.42
     litigation
    0.42
     blinking
    0.42
     twitter
    0.42
    Act Density 0.011%

    No Known Activations