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

    Neuronpedia

    INDEX
    Explanations

    panties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ivy
    -0.07
     нер
    -0.07
    ีเอ
    -0.06
     saturation
    -0.06
     invention
    -0.06
     Spar
    -0.06
     TP
    -0.06
     MAR
    -0.06
     websites
    -0.06
     student
    -0.06
    POSITIVE LOGITS
     disappears
    0.07
     Down
    0.07
     mantra
    0.06
     Whole
    0.06
    重大
    0.06
     ListTile
    0.06
    .Make
    0.06
     anno
    0.06
    excerpt
    0.06
     Understand
    0.06
    Act Density 0.000%

    No Known Activations