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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ini
    0.46
     Logos
    0.43
    ico
    0.39
     Locking
    0.38
    ida
    0.37
     Hyper
    0.37
    Hyper
    0.37
    ulagway
    0.36
    akkhati
    0.36
    ino
    0.36
    POSITIVE LOGITS
     puzzling
    0.45
     aead
    0.40
     domain
    0.39
     physic
    0.38
     даже
    0.38
     quantitative
    0.38
     veg
    0.38
     booze
    0.38
     ail
    0.37
     chieft
    0.37
    Act Density 0.000%

    No Known Activations