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

    Neuronpedia

    INDEX
    Explanations

    give a range

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rhizosphere
    0.47
     culturali
    0.46
     frameN
    0.45
     albumen
    0.45
     энергии
    0.45
     forage
    0.44
    羰
    0.43
     অনুবাদ
    0.43
     anthracene
    0.43
     anisotropy
    0.42
    POSITIVE LOGITS
     range
    0.45
     quiero
    0.44
     Range
    0.43
    ing
    0.43
    ia
    0.43
     People
    0.43
    atul
    0.43
     Chinese
    0.42
    Range
    0.42
     President
    0.42
    Act Density 0.003%

    No Known Activations