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

    Neuronpedia

    INDEX
    Explanations

    code, databases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    不知
    -0.07
    人才
    -0.06
    PublicKey
    -0.06
     ANAL
    -0.06
    —in
    -0.06
    мовір
    -0.06
    Unfortunately
    -0.06
     curing
    -0.06
     foil
    -0.06
    _SET
    -0.06
    POSITIVE LOGITS
     residence
    0.06
     production
    0.06
    rač
    0.06
    .TRAN
    0.06
     network
    0.06
    _field
    0.06
    .remote
    0.06
    _IND
    0.06
     alan
    0.05
     Pred
    0.05
    Act Density 0.039%

    No Known Activations