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

    Neuronpedia

    INDEX
    Explanations

    exact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oa̍t
    -0.58
     sonno
    -0.47
    olarmente
    -0.47
     lleve
    -0.46
     gynhyrchwyd
    -0.46
     réglable
    -0.45
    óngase
    -0.45
     fundamentales
    -0.44
     secar
    -0.44
    sile
    -0.43
    POSITIVE LOGITS
    0.75
    protoimpl
    0.71
    expandindo
    0.69
     Parac
    0.58
    territ
    0.58
     createContext
    0.57
    Filmo
    0.57
    YNAM
    0.56
    Aiheesta
    0.56
     Normdatei
    0.55
    Act Density 0.013%

    No Known Activations