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

    Neuronpedia

    INDEX
    Explanations

    Delegate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hacia
    -0.07
    -transitional
    -0.07
     bushes
    -0.07
     lenses
    -0.07
    velocity
    -0.07
     다운받
    -0.07
     التج
    -0.07
     ck
    -0.07
     taxonomy
    -0.07
     containers
    -0.06
    POSITIVE LOGITS
    .delegate
    0.07
    _delegate
    0.07
     README
    0.07
    δε
    0.07
    _deriv
    0.06
     balk
    0.06
    _ev
    0.06
    라
    0.06
     теб
    0.06
    βο
    0.06
    Act Density 0.003%

    No Known Activations