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

    Neuronpedia

    INDEX
    Explanations

    mathematical proofs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rempl
    -0.07
    purchase
    -0.07
     Asset
    -0.07
    据
    -0.07
    icemail
    -0.07
     estim
    -0.06
     passionate
    -0.06
     bishops
    -0.06
     석
    -0.06
    Mount
    -0.06
    POSITIVE LOGITS
    bc
    0.06
     BRE
    0.06
     beating
    0.06
     Fro
    0.06
    ufact
    0.05
     subtree
    0.05
    .n
    0.05
    -к
    0.05
    _HERE
    0.05
    DidLoad
    0.05
    Act Density 0.004%

    No Known Activations