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

    Neuronpedia

    INDEX
    Explanations

    reasoning/hypothetical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     atoi
    -0.09
    ತ್ಸ
    -0.08
     lottery
    -0.08
     handful
    -0.08
    Lottery
    -0.08
    Ә
    -0.08
    ხელ
    -0.08
     һә
    -0.07
    альнага
    -0.07
    әли
    -0.07
    POSITIVE LOGITS
     protr
    0.11
     curved
    0.10
     curvature
    0.10
     thickness
    0.10
     bending
    0.10
     angles
    0.09
     geometry
    0.09
     angled
    0.09
     tangent
    0.09
     thicker
    0.09
    Act Density 0.052%

    No Known Activations