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

    Neuronpedia

    INDEX
    Explanations

    Day

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Double
    -0.08
    /chart
    -0.07
    mean
    -0.07
     overhaul
    -0.07
    lean
    -0.07
    _Load
    -0.07
     joe
    -0.06
    提高
    -0.06
    uegos
    -0.06
    .modify
    -0.06
    POSITIVE LOGITS
    Accept
    0.08
     contin
    0.07
    主力
    0.07
    _UN
    0.07
    各国
    0.07
     İns
    0.07
     NP
    0.07
     PKK
    0.07
    political
    0.07
    nw
    0.07
    Act Density 0.035%

    No Known Activations