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

    Neuronpedia

    INDEX
    Explanations

    synthetic or foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     relying
    0.42
     errors
    0.39
     multid
    0.39
    Rounding
    0.38
     ethn
    0.38
     hashes
    0.38
     things
    0.38
     unpredictable
    0.37
     OSError
    0.37
     multi
    0.37
    POSITIVE LOGITS
     Schule
    0.46
    vacuum
    0.44
    akis
    0.43
    }}-\
    0.42
    MenuGroup
    0.42
    ೇವಿನ
    0.41
    Vacuum
    0.41
    anagram
    0.40
    romycin
    0.40
    厳
    0.39
    Act Density 0.000%

    No Known Activations