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

    Neuronpedia

    INDEX
    Explanations

    person

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LEN
    -0.07
    Encoding
    -0.07
    IXEL
    -0.07
    자의
    -0.07
    .HasPrefix
    -0.07
     connexion
    -0.07
    meeting
    -0.07
    Defense
    -0.06
     spread
    -0.06
    -picker
    -0.06
    POSITIVE LOGITS
     刘
    0.07
    563
    0.06
     perk
    0.06
     ト
    0.06
     выб
    0.06
     hlav
    0.06
    .tbl
    0.06
    (_:
    0.06
     frække
    0.06
     poh
    0.06
    Act Density 0.036%

    No Known Activations