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

    Neuronpedia

    INDEX
    Explanations

    advice and instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _dependencies
    -0.07
     gastr
    -0.07
    па
    -0.07
    figcaption
    -0.07
    -circle
    -0.07
     obj
    -0.06
     GM
    -0.06
    สะ
    -0.06
    inder
    -0.06
    pad
    -0.06
    POSITIVE LOGITS
    Meeting
    0.06
    ALLY
    0.06
     Prison
    0.06
     "'.
    0.06
    072
    0.05
     protestors
    0.05
    (parcel
    0.05
    .poll
    0.05
     upheld
    0.05
    前往
    0.05
    Act Density 0.025%

    No Known Activations