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

    Neuronpedia

    INDEX
    Explanations

    start of turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mtDNA
    0.39
     outro
    0.39
     maestro
    0.39
     stator
    0.39
    Pclass
    0.38
     gauss
    0.38
     glucocortic
    0.38
     calon
    0.37
     katana
    0.37
     demod
    0.36
    POSITIVE LOGITS
    <0x80>
    0.44
    Depending
    0.38
     Depending
    0.37
    depending
    0.35
     Whilst
    0.35
    Although
    0.35
    swering
    0.35
    而且
    0.35
    nın
    0.34
    While
    0.34
    Act Density 7.017%

    No Known Activations