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

    Neuronpedia

    INDEX
    Explanations

    subject

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vote
    -0.07
     foreign
    -0.07
     military
    -0.06
    dynamic
    -0.06
     prison
    -0.06
    stein
    -0.06
     vacation
    -0.06
     borderWidth
    -0.06
     bell
    -0.06
     深
    -0.06
    POSITIVE LOGITS
    ulumi
    0.07
    воз
    0.07
    LineStyle
    0.06
    liš
    0.06
    InstanceState
    0.06
    нив
    0.06
    приєм
    0.06
    elease
    0.06
     circa
    0.06
     Clears
    0.06
    Act Density 0.000%

    No Known Activations