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

    Neuronpedia

    INDEX
    Explanations

    hyphenation, spacing, 2-word combinations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     relapse
    0.44
    联邦
    0.39
    reti
    0.39
     retra
    0.39
     CLIP
    0.39
     maks
    0.39
     censorship
    0.39
    сії
    0.39
    образие
    0.38
    垦
    0.38
    POSITIVE LOGITS
     Addition
    0.39
    前往
    0.39
     awfully
    0.39
     F
    0.39
    PERS
    0.38
     Alphon
    0.38
    ♕
    0.37
    itter
    0.37
     Sport
    0.37
     ✓
    0.36
    Act Density 0.008%

    No Known Activations