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

    Neuronpedia

    INDEX
    Explanations

    subset of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    viewModel
    -0.08
     RemoteException
    -0.07
    рю
    -0.07
    chemistry
    -0.07
     phái
    -0.06
     pprint
    -0.06
     Gaussian
    -0.06
     reinforce
    -0.06
    freeze
    -0.06
    ometrics
    -0.06
    POSITIVE LOGITS
     x
    0.06
    .modified
    0.06
    发现
    0.06
     nick
    0.06
     carved
    0.06
     неб
    0.06
     meantime
    0.06
    _Form
    0.06
     Need
    0.06
     Fail
    0.06
    Act Density 0.052%

    No Known Activations