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

    Neuronpedia

    INDEX
    Explanations

    lith

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [model
    -0.07
    Velocity
    -0.07
    eros
    -0.07
    Eigen
    -0.06
     Cancel
    -0.06
    _MAY
    -0.06
    indrome
    -0.06
     يمكن
    -0.06
     Zoom
    -0.06
    ektor
    -0.06
    POSITIVE LOGITS
     lith
    0.17
     Lith
    0.13
    olith
    0.13
    ith
    0.09
    ITH
    0.09
     lithium
    0.08
     лит
    0.08
    石
    0.07
     Roth
    0.07
    portion
    0.07
    Act Density 0.002%

    No Known Activations