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

    Neuronpedia

    INDEX
    Explanations

    sagas, eventual consistency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     слова
    -0.08
    onso
    -0.08
    _sock
    -0.08
    <stdio
    -0.08
    ieh
    -0.08
     densely
    -0.08
    Orth
    -0.07
    wur
    -0.07
     Orth
    -0.07
     Dense
    -0.07
    POSITIVE LOGITS
     reconc
    0.09
     reconciliation
    0.08
    infra
    0.08
    	long
    0.08
    /pay
    0.07
     paradig
    0.07
    conciliation
    0.07
    /privacy
    0.07
     élég
    0.07
    ='/
    0.07
    Act Density 0.001%

    No Known Activations