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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    范
    -0.08
     fossil
    -0.07
    璞
    -0.07
     tray
    -0.07
    Ν
    -0.07
     indiv
    -0.07
    -icon
    -0.06
    㺄
    -0.06
    ']
    -0.06
     strstr
    -0.06
    POSITIVE LOGITS
    .Quantity
    0.08
    LB
    0.08
    Seek
    0.08
    duction
    0.07
    rowth
    0.07
     gradients
    0.07
    约束
    0.07
    /ca
    0.07
    Cells
    0.07
    crit
    0.07
    Act Density 0.002%

    No Known Activations