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

    Neuronpedia

    INDEX
    Explanations

    Indemnity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     найбільш
    -0.07
    STRING
    -0.07
     Weapons
    -0.07
     surtout
    -0.07
    "default
    -0.07
    .SetBool
    -0.06
    .Elements
    -0.06
    List
    -0.06
     관
    -0.06
     weaknesses
    -0.06
    POSITIVE LOGITS
     indemn
    0.11
    inoa
    0.07
    -educated
    0.07
    chema
    0.07
     режим
    0.06
     stát
    0.06
     inclination
    0.06
     Uy
    0.06
    pect
    0.06
    telephone
    0.06
    Act Density 0.001%

    No Known Activations