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

    Neuronpedia

    INDEX
    Explanations

    kappa

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    252
    -0.08
    .***.***
    -0.07
     weakest
    -0.07
     Medi
    -0.07
     identify
    -0.06
     taken
    -0.06
    ,,,,,,,,
    -0.06
     grievances
    -0.06
     #####
    -0.06
    interval
    -0.06
    POSITIVE LOGITS
    _AFTER
    0.07
    (sockfd
    0.07
     ami
    0.07
    (created
    0.07
    ệnh
    0.06
    ecret
    0.06
     eğit
    0.06
    εν
    0.06
     airspace
    0.06
     :|:
    0.06
    Act Density 0.014%

    No Known Activations