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

    Neuronpedia

    INDEX
    Explanations

    code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0xE1>
    0.57
    akah
    0.53
    unlock
    0.51
     offre
    0.50
    ocarbon
    0.50
     upor
    0.49
    ocas
    0.49
    ᑐ
    0.49
     kun
    0.49
    oca
    0.49
    POSITIVE LOGITS
     ilusión
    0.69
     factoryName
    0.66
     gardens
    0.65
     prostitutes
    0.63
    windowActionBar
    0.62
     greenery
    0.60
    Asked
    0.60
     जड़ों
    0.58
    Basically
    0.57
     Basically
    0.57
    Act Density 0.108%

    No Known Activations