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

    Neuronpedia

    INDEX
    Explanations

    cell resistance/apoptosis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Screens
    -0.06
    ाइन
    -0.06
    _RX
    -0.06
    _area
    -0.06
     irrational
    -0.06
     Hooks
    -0.06
     cannot
    -0.06
    191
    -0.06
    .indices
    -0.06
     numpy
    -0.06
    POSITIVE LOGITS
     Canadians
    0.07
    ève
    0.07
    -speed
    0.06
    -quality
    0.06
     contestant
    0.06
    lobber
    0.06
    amm
    0.06
    стре
    0.06
    rf
    0.06
     clientele
    0.06
    Act Density 0.039%

    No Known Activations